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

    Neuronpedia

    INDEX
    Explanations

    API documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     t
    0.77
     it
    0.61
     $
    0.58
    !"
    0.58
    ท
    0.58
     wasn
    0.56
    ير
    0.55
    id
    0.55
    cud
    0.54
     as
    0.54
    POSITIVE LOGITS
    <0xB2>
    0.66
    ⚊
    0.60
     चरित्र
    0.56
    的
    0.56
     कोटा
    0.55
    doğan
    0.54
    น้ำ
    0.54
    abaya
    0.54
    úrate
    0.54
    ionalità
    0.54
    Act Density 0.000%

    No Known Activations