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

    Neuronpedia

    INDEX
    Explanations

    quotation marks or new items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ి
    1.54
    Keyword
    1.37
     uttered
    1.35
    igay
    1.34
     mischiev
    1.34
    }";
    1.31
    倣
    1.31
    吘
    1.31
    方的
    1.29
    니다
    1.29
    POSITIVE LOGITS
    ৭
    1.48
     estar
    1.31
     mulig
    1.30
     ito
    1.27
    ют
    1.23
    ல்
    1.22
     essere
    1.21
     hali
    1.18
     odds
    1.17
    اشت
    1.17
    Act Density 0.003%

    No Known Activations