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

    Neuronpedia

    INDEX
    Explanations

    device

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    眼
    -0.07
    家
    -0.06
    j
    -0.06
    ulner
    -0.06
     NES
    -0.06
    _APPEND
    -0.06
    ileges
    -0.06
    dı
    -0.06
    적으로
    -0.06
    500
    -0.06
    POSITIVE LOGITS
    网址
    0.06
     XXX
    0.06
    boundary
    0.06
    騎
    0.06
    증금
    0.06
     contr
    0.06
     propos
    0.06
    -Ass
    0.06
    ременно
    0.06
     quotation
    0.06
    Act Density 0.010%

    No Known Activations