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

    Neuronpedia

    INDEX
    Explanations

    Day 1 itinerary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    em
    0.43
    &=
    0.41
    be
    0.39
     Valerie
    0.39
    ass
    0.39
    us
    0.38
    huang
    0.38
    ħ
    0.37
    W
    0.37
    ur
    0.37
    POSITIVE LOGITS
     فيدي
    0.37
     অন্যতম
    0.36
    供应链
    0.36
     環境
    0.36
     destinado
    0.36
     kucch
    0.36
     tasse
    0.36
     sahab
    0.36
     Fintech
    0.35
     ഇക്കാര
    0.35
    Act Density 0.013%

    No Known Activations