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

    Neuronpedia

    INDEX
    Explanations

    Query, currents, debris removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗼
    1.18
    𝘀
    1.16
    өлү
    1.14
    ל
    1.14
    ول
    1.13
    о
    1.13
    ді
    1.09
    ли
    1.08
    та
    1.08
     myös
    1.08
    POSITIVE LOGITS
    fim
    0.96
    elar
    0.95
    윽
    0.95
    Excelente
    0.93
    फॉ
    0.92
    cd
    0.92
    If
    0.89
    fes
    0.89
    Fonte
    0.88
    fst
    0.86
    Act Density 0.002%

    No Known Activations