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

    Neuronpedia

    INDEX
    Explanations

    status quo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.95
    hydraz
    0.93
    митри
    0.91
    truck
    0.89
    ীভূত
    0.87
    h
    0.87
     রে
    0.86
     surfaced
    0.86
    indexer
    0.86
    RATE
    0.85
    POSITIVE LOGITS
     quo
    2.56
     nasc
    1.62
     quos
    1.60
     epileptic
    1.31
    การณ์
    1.27
    UTORY
    1.16
    码
    1.16
    ssss
    1.15
    quo
    1.07
    EMENTS
    1.03
    Act Density 0.043%

    No Known Activations