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

    Neuronpedia

    INDEX
    Explanations

    `fn main`, REM, csv

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    보
    0.46
    ነ
    0.45
    チラ
    0.44
    핀
    0.43
     reusable
    0.42
    سل
    0.41
    ارين
    0.41
     authorisation
    0.40
    流行
    0.40
    上
    0.40
    POSITIVE LOGITS
    efined
    0.44
     Started
    0.43
     sviluppo
    0.42
     Carefully
    0.42
     menjalani
    0.41
     leggere
    0.40
     могла
    0.40
     ഇതി
    0.40
    -/-
    0.40
     साव
    0.40
    Act Density 0.002%

    No Known Activations