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

    Neuronpedia

    INDEX
    Explanations

    listening to music

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.79
     invigorating
    0.73
    ل
    0.71
    ről
    0.71
     மிசோரம்
    0.71
    lj
    0.68
    ोत
    0.68
    cs
    0.67
    ků
    0.66
    Ги
    0.64
    POSITIVE LOGITS
    ן
    1.00
    দের
    0.97
    ರ
    0.89
    ;
    0.80
    ı
    0.77
    ad
    0.77
    ियों
    0.77
    },$
    0.75
    od
    0.74
    తో
    0.74
    Act Density 0.025%

    No Known Activations