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

    Neuronpedia

    INDEX
    Explanations

    describing past actions and intentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     headwinds
    0.70
    ofd
    0.67
    andı
    0.64
    最初に
    0.63
     covariates
    0.62
    ASSI
    0.61
    ইহার
    0.61
     ಮುಖ್ಯ
    0.61
    ofan
    0.60
     बढ़ती
    0.60
    POSITIVE LOGITS
    س
    1.40
    ت
    1.21
    ל
    1.14
    ن
    0.98
    র
    0.95
     been
    0.93
    ש
    0.91
    );
    0.90
    с
    0.90
    י
    0.84
    Act Density 0.236%

    No Known Activations