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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Associate
    -0.07
    ۲۰۰
    -0.07
    4
    -0.07
    -bl
    -0.07
    ’app
    -0.07
    -з
    -0.06
     tribes
    -0.06
    μφωνα
    -0.06
    .reserve
    -0.06
    มาร
    -0.06
    POSITIVE LOGITS
    Vectorizer
    0.07
    ời
    0.06
     AMD
    0.06
    、あ
    0.06
    оказ
    0.06
     sahip
    0.06
    Signature
    0.06
     signify
    0.06
    inky
    0.06
     realmente
    0.06
    Act Density 0.010%

    No Known Activations