Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Contrasting statements

    np_max-act · gemini-2.0-flash

    discussions about political complexities and challenges related to peace processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron primarily picks out descriptive modifiers—especially adjectives and adverbs that convey intensity or emphasis.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     TypeError
    -0.07
     palms
    -0.07
     Teh
    -0.07
     opposite
    -0.07
     Mourinho
    -0.06
     MIS
    -0.06
    udur
    -0.06
     newArr
    -0.06
    yr
    -0.06
     velik
    -0.06
    POSITIVE LOGITS
    _processor
    0.07
     compromises
    0.07
    _leave
    0.06
    participant
    0.06
     solitude
    0.06
    َد
    0.06
     क
    0.06
    .repositories
    0.06
    诗
    0.06
     protections
    0.06
    Act Density 0.071%

    No Known Activations