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

    Neuronpedia

    INDEX
    Explanations

    documentation strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icono
    0.62
    break
    0.61
    inska
    0.58
    =>
    0.57
     কিন্ত
    0.57
     காட்சி
    0.57
     रिटर्न
    0.56
    стка
    0.56
    بر
    0.56
    తలు
    0.56
    POSITIVE LOGITS
    始める
    0.74
     включают
    0.74
    Determination
    0.74
    رحمن
    0.73
     இடை
    0.72
    的光
    0.71
     kasutada
    0.71
     नाइट्र
    0.71
    ревнова
    0.71
     determination
    0.70
    Act Density 0.096%

    No Known Activations