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

    Neuronpedia

    INDEX
    Explanations

    rules and requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ообраз
    -0.06
     planning
    -0.06
     情
    -0.06
     ug
    -0.06
     discomfort
    -0.06
    igos
    -0.06
     perfume
    -0.06
    иболее
    -0.06
     док
    -0.06
     參
    -0.06
    POSITIVE LOGITS
    xml
    0.06
    (cart
    0.06
    idents
    0.06
    .Down
    0.06
    .lang
    0.06
    [].
    0.06
     LEG
    0.06
    rupt
    0.06
    ество
    0.06
    \Form
    0.05
    Act Density 0.156%

    No Known Activations