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

    Neuronpedia

    INDEX
    Explanations

    object identity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     panor
    -0.08
    ieß
    -0.07
     adn
    -0.07
    取得
    -0.07
    ಿಕೊಂಡ
    -0.07
     welcoming
    -0.07
     backgrounds
    -0.07
     pen
    -0.07
    óso
    -0.07
     for
    -0.07
    POSITIVE LOGITS
     RNG
    0.09
     אמת
    0.09
     ورب
    0.08
     ouder
    0.08
     vật
    0.08
     հիշ
    0.08
    /random
    0.08
     nonetheless
    0.08
     বর
    0.08
    ൊരു
    0.07
    Act Density 0.003%

    No Known Activations