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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UNCIL
    0.35
    ATION
    0.35
     VIEW
    0.35
     聞い
    0.35
    CAUSE
    0.34
     உள்ளட
    0.34
    IMENTO
    0.33
    濘
    0.33
    ULATION
    0.32
    లేదు
    0.32
    POSITIVE LOGITS
    Beware
    0.39
     jangan
    0.38
     nochmal
    0.37
     legjobb
    0.35
    île
    0.34
    obranch
    0.34
    ávat
    0.34
    ॐ
    0.34
     fáciles
    0.34
    Jangan
    0.34
    Act Density 0.001%

    No Known Activations