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

    Neuronpedia

    INDEX
    Explanations

    tour guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.73
    ו
    0.70
    ח
    0.68
    s
    0.65
    an
    0.63
    و
    0.63
    ی
    0.63
    ش
    0.61
    al
    0.59
    IT
    0.59
    POSITIVE LOGITS
    도
    0.58
     ίδια
    0.58
     tours
    0.57
     बल्ले
    0.55
     tournée
    0.55
     considérée
    0.54
    गुना
    0.54
    勍
    0.54
     inversa
    0.54
    𝚣
    0.54
    Act Density 0.002%

    No Known Activations