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

    Neuronpedia

    INDEX
    Explanations

    self-reference

    np_max-act · gemini-2.0-flash

    The neuron responds to past‐perfect verb phrases (in particular “had” followed by a past participle).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bean
    -0.07
    _TYPES
    -0.07
     своей
    -0.06
    .setName
    -0.06
    /service
    -0.06
    िब
    -0.06
    osed
    -0.06
     glaciers
    -0.06
    授
    -0.06
    Configuration
    -0.06
    POSITIVE LOGITS
     kas
    0.07
     SQLite
    0.07
     dak
    0.07
    _SOL
    0.07
     Bian
    0.07
     착
    0.06
    agenda
    0.06
    824
    0.06
    .twimg
    0.06
    .imag
    0.06
    Act Density 0.028%

    No Known Activations