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

    Neuronpedia

    INDEX
    Explanations

    named entities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mm
    0.60
    rane
    0.59
    eder
    0.59
    nerg
    0.58
    block
    0.58
    uu
    0.57
    umoto
    0.57
    ve
    0.56
    pean
    0.55
    ar
    0.54
    POSITIVE LOGITS
     Sergey
    0.70
     Antony
    0.69
     espè
    0.67
     siêu
    0.67
     FRANCIS
    0.66
     superson
    0.65
     Olga
    0.65
     школова
    0.65
     Šk
    0.65
     秒
    0.65
    Act Density 0.001%

    No Known Activations