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

    Neuronpedia

    INDEX
    Explanations

    topics and subsequent service nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    im
    0.79
    ed
    0.77
    är
    0.70
    ın
    0.69
    ar
    0.69
    á
    0.66
    و
    0.66
    en
    0.66
    ной
    0.64
    其他
    0.64
    POSITIVE LOGITS
     polytopes
    0.69
    ቬ
    0.68
     hôtels
    0.64
    ﹁
    0.64
     condos
    0.64
    ኺ
    0.64
     Decatur
    0.63
    𝚆
    0.63
     aphids
    0.63
     projektu
    0.62
    Act Density 0.475%

    No Known Activations