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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    篼
    -0.08
    fieldName
    -0.07
    userinfo
    -0.07
    然後
    -0.07
     мог
    -0.07
    党组书记
    -0.07
    佣
    -0.07
     between
    -0.06
     dispenser
    -0.06
     EUR
    -0.06
    POSITIVE LOGITS
    .nick
    0.07
     Brick
    0.07
     Augustine
    0.07
    .std
    0.07
    _rf
    0.07
    랍
    0.07
    _clicked
    0.07
     vocab
    0.06
     Shows
    0.06
    ]='\
    0.06
    Act Density 0.046%

    No Known Activations