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

    Neuronpedia

    INDEX
    Explanations

    type safety and mechanics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Supply
    0.43
    úrate
    0.40
    Wing
    0.39
    BOUND
    0.38
     ন
    0.37
     ornaments
    0.36
    Bound
    0.36
    VisualStyle
    0.35
    बा
    0.35
     Supply
    0.35
    POSITIVE LOGITS
     हल्दी
    0.41
    redni
    0.38
     contributed
    0.38
    ಿಣ
    0.38
    放出
    0.37
     ~,
    0.36
    ACH
    0.35
    acch
    0.35
     discriminatory
    0.35
     విడు
    0.35
    Act Density 0.002%

    No Known Activations