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

    Neuronpedia

    INDEX
    Explanations

    year to year, word by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۰۰
    1.08
     volle
    1.07
    ্ধ্য
    1.05
     momento
    1.01
     envis
    1.01
    вні
    1.01
    ्यास
    0.98
    cte
    0.97
     multe
    0.96
    seleccion
    0.95
    POSITIVE LOGITS
    erView
    1.03
    €™
    1.03
     astray
    1.01
    Clothes
    1.00
    BigAutoField
    0.99
    ੍ਹ
    0.98
    ب
    0.96
    Ako
    0.96
    CoA
    0.95
    occur
    0.95
    Act Density 0.010%

    No Known Activations