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

    Neuronpedia

    INDEX
    Explanations

    items or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাসস্থান
    0.48
     Фи
    0.48
    idades
    0.47
    iter
    0.47
    hitung
    0.47
    িবাস
    0.45
     стаби
    0.44
     試験
    0.43
    uchte
    0.43
     Фин
    0.40
    POSITIVE LOGITS
    ز
    0.49
    ا
    0.48
     omfatt
    0.46
     egregious
    0.45
     nefarious
    0.45
     ओर
    0.44
     lhs
    0.44
     năm
    0.43
     surnames
    0.43
     erhält
    0.43
    Act Density 0.044%

    No Known Activations