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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    投标
    -0.08
    跖
    -0.07
     multinational
    -0.07
    uden
    -0.07
    Und
    -0.07
    _transactions
    -0.07
     uluslararası
    -0.07
    内幕
    -0.06
    寨
    -0.06
    ordinal
    -0.06
    POSITIVE LOGITS
    .builder
    0.07
    released
    0.07
     Separate
    0.07
    Gre
    0.07
    넉
    0.07
    eller
    0.07
     FEATURES
    0.06
    /MM
    0.06
    物
    0.06
     groß
    0.06
    Act Density 0.028%

    No Known Activations