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

    Neuronpedia

    INDEX
    Explanations

    Al-Qaeda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הש
    0.31
     x
    0.29
     ער
    0.28
     ошибка
    0.28
     Solving
    0.27
     mean
    0.27
     hydrate
    0.27
     ли
    0.27
     מה
    0.26
     Things
    0.26
    POSITIVE LOGITS
     Nutzung
    0.34
    ado
    0.32
     Auf
    0.32
     Schwerpunkt
    0.32
    maq
    0.32
    ichtung
    0.32
     همه
    0.32
    doa
    0.31
    ada
    0.31
    gah
    0.31
    Act Density 0.001%

    No Known Activations