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

    Neuronpedia

    INDEX
    Explanations

    appeasement toward, direct inheritance, HTTP proxies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.45
    的公司
    0.43
    ur
    0.43
    ipp
    0.41
    აზე
    0.41
    و
    0.40
    ا
    0.40
    developers
    0.40
    trees
    0.39
    rit
    0.39
    POSITIVE LOGITS
     froze
    0.46
     natür
    0.43
     manhã
    0.42
     congel
    0.42
     méth
    0.41
     États
    0.41
     adhé
    0.40
     الطاقة
    0.40
     "."
    0.40
     ඉ
    0.40
    Act Density 0.001%

    No Known Activations