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

    Neuronpedia

    INDEX
    Explanations

    1 or first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tougher
    -0.07
    ベル
    -0.07
     *__
    -0.06
    }->
    -0.06
    .getStyle
    -0.06
     lighten
    -0.06
     lowering
    -0.06
    incinn
    -0.06
    린이
    -0.06
     alta
    -0.06
    POSITIVE LOGITS
     Voters
    0.07
    長
    0.06
    (rel
    0.06
     hombre
    0.06
     renowned
    0.06
    atism
    0.06
    长
    0.06
    Lot
    0.06
     Marketable
    0.06
     depend
    0.06
    Act Density 0.033%

    No Known Activations