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

    Neuronpedia

    INDEX
    Explanations

    not horror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EXCLUSIVE
    1.10
     cousin
    1.04
     dva
    1.02
    Former
    1.02
     coupons
    0.97
    suffix
    0.97
    with
    0.97
    Money
    0.96
    Courtesy
    0.96
     इन्हीं
    0.96
    POSITIVE LOGITS
    整个
    1.49
     keseluruhan
    1.47
    整個
    1.39
     tumorigen
    1.38
     создании
    1.37
     carcinogenesis
    1.35
     funcionamento
    1.34
    determining
    1.34
    versation
    1.33
     operación
    1.32
    Act Density 1.277%

    No Known Activations