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

    Neuronpedia

    INDEX
    Explanations

    characterized by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.76
     år
    0.70
    en
    0.67
     μ
    0.66
    𝑒
    0.64
    ان
    0.63
    é
    0.63
     $
    0.62
     мі
    0.62
     ölç
    0.61
    POSITIVE LOGITS
    зыва
    0.72
    な
    0.66
    ール
    0.64
    was
    0.63
    キャン
    0.62
    ヴィトン
    0.60
    特徴
    0.60
    失敗
    0.59
    avas
    0.59
     특징
    0.59
    Act Density 0.031%

    No Known Activations