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

    Neuronpedia

    INDEX
    Explanations

    Central Asian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.63
    E
    0.60
    P
    0.57
    ק
    0.57
    ق
    0.56
    R
    0.55
     في
    0.55
    in
    0.54
    ب
    0.54
     osoba
    0.52
    POSITIVE LOGITS
    ᱔
    0.63
    ⇉
    0.60
     تک
    0.58
     منجر
    0.57
     نیز
    0.57
    ۔۔۔۔
    0.57
    .•
    0.55
    منٹ
    0.55
    ・・・・
    0.54
    َی
    0.54
    Act Density 0.000%

    No Known Activations