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

    Neuronpedia

    INDEX
    Explanations

    say disclaimer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sürek
    -0.07
     Corey
    -0.07
     ----------------------------------------------------------------------------
    -0.07
     sàng
    -0.06
    unteers
    -0.06
    続け
    -0.06
    伴随
    -0.06
    شخصيات
    -0.06
     satisfying
    -0.06
     air
    -0.06
    POSITIVE LOGITS
     Scope
    0.08
     tapes
    0.07
    שט
    0.07
    发展方向
    0.07
    quist
    0.06
    賺
    0.06
    _CREATE
    0.06
    über
    0.06
     spokes
    0.06
    bp
    0.06
    Act Density 0.003%

    No Known Activations