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

    Neuronpedia

    INDEX
    Explanations

    dependency repositories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olese
    1.80
    ಬ್ಬಿಣ
    1.80
    ((\
    1.78
    xyl
    1.70
    ceived
    1.69
    orems
    1.66
    ろん
    1.61
    \\
    1.59
    avali
    1.59
    ,\,
    1.58
    POSITIVE LOGITS
    ن
    2.57
    га
    2.13
    en
    2.05
    ా
    1.93
    ו
    1.93
     входят
    1.93
    лаго
    1.88
    та
    1.84
    ح
    1.76
     arid
    1.75
    Act Density 0.000%

    No Known Activations