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

    Neuronpedia

    INDEX
    Explanations

    employee intranet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    0.44
     உள்ளிட்ட
    0.41
    ne
    0.41
    OD
    0.38
    the
    0.37
    De
    0.37
    ot
    0.36
    def
    0.36
    yl
    0.35
     இணைந்து
    0.35
    POSITIVE LOGITS
     prostit
    0.39
     raping
    0.39
     naciones
    0.38
     প্রতার
    0.37
     craziness
    0.37
     Москвы
    0.37
     underdog
    0.37
     bullies
    0.36
     odio
    0.35
     corrupción
    0.35
    Act Density 0.001%

    No Known Activations