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

    Neuronpedia

    INDEX
    Explanations

    abrupt events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     correspondent
    -0.09
    istes
    -0.08
    īj
    -0.08
     Maintenance
    -0.08
    Peso
    -0.08
     ผ
    -0.08
    己
    -0.07
    allon
    -0.07
    rello
    -0.07
     жүргіз
    -0.07
    POSITIVE LOGITS
     abrupt
    0.11
     transition
    0.10
     sudden
    0.09
    方式
    0.09
     dramatic
    0.09
     संक्रमण
    0.09
     अचानक
    0.09
     حدوث
    0.09
     Überg
    0.09
     overgang
    0.08
    Act Density 0.125%

    No Known Activations