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

    Neuronpedia

    INDEX
    Explanations

    foreign text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prof
    0.61
     menc
    0.55
     Vir
    0.54
     )\
    0.54
    )\
    0.54
    }\
    0.53
    &\
    0.52
    current
    0.52
    beam
    0.52
    צ
    0.52
    POSITIVE LOGITS
     înviat
    0.71
    日記
    0.65
     المسؤول
    0.64
     paheli
    0.63
    0.61
     Responsibility
    0.61
     গার্ডিয়ান
    0.60
    новниш
    0.59
     ansvar
    0.59
    स्ता
    0.59
    Act Density 0.000%

    No Known Activations