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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash

    The neuron activates on institution or affiliation names in academic paper metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .charset
    -0.07
    :{
    -0.06
     contrary
    -0.06
     world
    -0.06
     Multimedia
    -0.06
    _movies
    -0.06
    371
    -0.06
     світ
    -0.06
     cast
    -0.06
    اید
    -0.06
    POSITIVE LOGITS
     velik
    0.07
    hood
    0.06
     Vibr
    0.06
    Дж
    0.06
     PLEASE
    0.06
    uppe
    0.06
     Fortunately
    0.06
     Igor
    0.06
     ripe
    0.06
     mutation
    0.06
    Act Density 0.009%

    No Known Activations