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

    Neuronpedia

    INDEX
    Explanations

    processing provided information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.86
    ق
    0.84
    ad
    0.84
    in
    0.78
    ar
    0.75
    ic
    0.71
    al
    0.71
    ap
    0.71
    u
    0.70
    et
    0.66
    POSITIVE LOGITS
    х
    0.67
    ИН
    0.65
    ERS
    0.63
    き
    0.62
    อย่าง
    0.61
     immobil
    0.60
     в
    0.59
    ה
    0.59
    なく
    0.58
    ال
    0.58
    Act Density 1.082%

    No Known Activations