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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Axis
    -0.08
     explode
    -0.06
    .tile
    -0.06
     Yuri
    -0.06
    .div
    -0.06
    olk
    -0.06
    _CONSTANT
    -0.06
     App
    -0.06
    TECTED
    -0.06
     Restore
    -0.06
    POSITIVE LOGITS
    ANGO
    0.07
    .dump
    0.07
     Queries
    0.07
    unctuation
    0.06
    깨
    0.06
    usuarios
    0.06
     الأ
    0.06
     萬
    0.06
    배송
    0.06
     cooperating
    0.06
    Act Density 0.003%

    No Known Activations