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

    Neuronpedia

    INDEX
    Explanations

    by substituting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Electronic
    0.74
     Secret
    0.74
    特色
    0.73
     skills
    0.71
    Secret
    0.70
     tone
    0.69
     secrets
    0.68
     ayrı
    0.68
     ưa
    0.68
     toned
    0.67
    POSITIVE LOGITS
     scenario
    0.88
     maximale
    0.85
     Scenario
    0.85
    maximum
    0.83
    Scenario
    0.83
    max
    0.79
     homozygous
    0.79
    Example
    0.79
    Suppose
    0.78
     maximum
    0.77
    Act Density 1.890%

    No Known Activations