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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    独
    -0.06
     теат
    -0.06
     Wisdom
    -0.06
    _lambda
    -0.06
     hanging
    -0.06
    ↢
    -0.06
    twenty
    -0.06
    trade
    -0.06
    qry
    -0.06
    快三
    -0.06
    POSITIVE LOGITS
     cải
    0.07
     County
    0.07
    述
    0.07
    _fee
    0.07
     получен
    0.06
    前述
    0.06
     corresponds
    0.06
    <>
    0.06
    退
    0.06
    빪
    0.06
    Act Density 0.135%

    No Known Activations