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

    Neuronpedia

    INDEX
    Explanations

    bicep curls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atm
    1.56
    1.46
    IER
    1.45
    ATION
    1.45
    اد
    1.40
    Б
    1.39
     Int
    1.38
     Organization
    1.38
    Би
    1.38
    izes
    1.36
    POSITIVE LOGITS
    ش
    1.81
    на
    1.66
    нде
    1.59
    те
    1.58
    ꯋ
    1.57
    м
    1.55
    쿱
    1.47
    ला
    1.43
    ৪০
    1.43
     Gabby
    1.41
    Act Density 0.000%

    No Known Activations