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

    Neuronpedia

    INDEX
    Explanations

    dependency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pw
    -0.07
     kla
    -0.07
     Clock
    -0.06
     Німеч
    -0.06
    任
    -0.06
     addUser
    -0.06
     центра
    -0.06
    내
    -0.06
    missive
    -0.06
     чим
    -0.06
    POSITIVE LOGITS
    articles
    0.07
    Wa
    0.06
    -trade
    0.06
     accounted
    0.06
    _dec
    0.06
    ститут
    0.06
     freshman
    0.06
    .JButton
    0.06
     leaf
    0.06
    ("./
    0.06
    Act Density 0.002%

    No Known Activations