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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Random
    -0.07
    ']),↵
    -0.06
     PID
    -0.06
    ंद
    -0.06
     Dis
    -0.06
     Mej
    -0.06
    吐
    -0.06
     jerk
    -0.06
    _Format
    -0.06
     counseling
    -0.06
    POSITIVE LOGITS
    (ERR
    0.06
    าช
    0.06
    、お
    0.06
    EXPR
    0.06
    /************************************************************************
    0.06
    どう
    0.06
    母亲
    0.06
    Лю
    0.06
    iness
    0.06
     sợ
    0.06
    Act Density 0.389%

    No Known Activations