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

    Neuronpedia

    INDEX
    Explanations

    latex math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ları
    3.07
    İlk
    2.86
     sujet
    2.77
    べき
    2.70
     coax
    2.70
    शिप
    2.63
    érature
    2.60
    еру
    2.59
     conocidas
    2.58
     uomo
    2.58
    POSITIVE LOGITS
    bibfnamefont
    3.83
    क
    3.40
    et
    3.34
     ${\
    3.03
    특별시
    2.93
    なって
    2.82
    el
    2.77
    な
    2.77
    ্ড
    2.66
    м
    2.65
    Act Density 0.002%

    No Known Activations