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

    Neuronpedia

    INDEX
    Explanations

    data quality assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Upload
    0.39
    ASY
    0.38
     cfg
    0.38
    Asc
    0.38
    EMT
    0.38
    GPIO
    0.37
    ]!=
    0.37
    entos
    0.36
    ingh
    0.36
    actica
    0.36
    POSITIVE LOGITS
     počíta
    0.42
    ಣೆ
    0.40
    ன
    0.39
     Verhältnis
    0.38
     calling
    0.38
     впечатление
    0.38
     maß
    0.38
     laissé
    0.38
     laisser
    0.38
     מד
    0.37
    Act Density 0.000%

    No Known Activations