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

    Neuronpedia

    INDEX
    Explanations

    Ford F-Series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    रासत
    0.85
    ال
    0.79
    トップス
    0.76
    សម្
    0.73
    ்ச
    0.73
    ُ
    0.73
    وا
    0.73
    یدی
    0.73
     ljudi
    0.72
    affirm
    0.72
    POSITIVE LOGITS
    >().
    0.86
     instância
    0.81
     бывают
    0.80
     оболо
    0.80
    কৃত
    0.78
    >();
    0.77
    >(
    0.75
     are
    0.74
    >>::
    0.74
     만드는
    0.73
    Act Density 0.000%

    No Known Activations