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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    0.45
     tahap
    0.43
     εκ
    0.42
     senha
    0.42
    اتھ
    0.41
    omyosin
    0.41
     medicamentos
    0.40
    yyati
    0.40
     ervaring
    0.40
    ंद्र
    0.39
    POSITIVE LOGITS
     causality
    1.33
     causal
    1.24
     Caus
    1.16
     causation
    1.12
     caus
    0.97
    Cause
    0.92
     причин
    0.92
     cause
    0.86
     Cause
    0.84
     causa
    0.80
    Act Density 0.008%

    No Known Activations