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

    Neuronpedia

    INDEX
    Explanations

    find a way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saludos
    1.04
    StringBuffer
    0.92
     aucune
    0.92
     क्वांटिटी
    0.91
    gameField
    0.91
     martens
    0.90
     aby
    0.88
     botched
    0.88
     чтобы
    0.88
     смысла
    0.88
    POSITIVE LOGITS
    на
    0.97
    a
    0.95
    aquest
    0.85
    isia
    0.81
    isme
    0.80
    ion
    0.80
    هِ
    0.79
    ați
    0.78
    াজার
    0.76
    לח
    0.76
    Act Density 0.172%

    No Known Activations