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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting like `:*`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     precedent
    0.43
     технологий
    0.43
    ク
    0.43
    クリ
    0.42
     beschikbaar
    0.42
    UO
    0.42
    BANK
    0.41
    veri
    0.40
    Metadata
    0.40
     クリ
    0.39
    POSITIVE LOGITS
    שרה
    0.56
    ితో
    0.46
    ϓ
    0.46
    ържа
    0.44
    ᱘
    0.44
     Fraction
    0.43
    ৫
    0.43
    ைச்
    0.42
    ைத்
    0.42
    াস্থ্য
    0.42
    Act Density 0.001%

    No Known Activations