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

    Neuronpedia

    INDEX
    Explanations

    positive comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.82
    el
    0.79
    ت
    0.77
    icited
    0.77
    id
    0.74
    usd
    0.74
     cuento
    0.72
    هه
    0.71
    hsl
    0.71
    is
    0.70
    POSITIVE LOGITS
     וא
    0.86
     cada
    0.76
    页面存档备份
    0.76
     ג
    0.75
     αυτό
    0.75
     კ
    0.71
    போது
    0.70
     Эта
    0.70
     videog
    0.70
     kanker
    0.68
    Act Density 0.000%

    No Known Activations