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

    Neuronpedia

    INDEX
    Explanations

    files, scripts, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALLOW
    -0.07
    .Ex
    -0.07
    受
    -0.06
     capacities
    -0.06
     autofocus
    -0.06
     arrayList
    -0.06
    うち
    -0.06
     felony
    -0.06
     ArrayList
    -0.06
     talk
    -0.06
    POSITIVE LOGITS
    amento
    0.07
     تای
    0.07
    ادن
    0.06
    чення
    0.06
    @gmail
    0.06
     レディース
    0.06
     дея
    0.06
     lavor
    0.06
     jspb
    0.06
    ển
    0.06
    Act Density 0.011%

    No Known Activations