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

    Neuronpedia

    INDEX
    Explanations

    available to the public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    είο
    0.41
     кристал
    0.40
    Chill
    0.39
     Chill
    0.37
     backbone
    0.37
    ッチン
    0.37
     anywhere
    0.37
    ேயே
    0.37
     ショ
    0.36
    绛
    0.36
    POSITIVE LOGITS
    public
    0.48
    urant
    0.42
    Public
    0.41
    cy
    0.40
     al
    0.39
     public
    0.39
    bor
    0.38
    atus
    0.38
    ury
    0.37
    اصل
    0.37
    Act Density 0.009%

    No Known Activations