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

    Neuronpedia

    INDEX
    Explanations

    species and house structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৫
    0.65
     बच्चे
    0.62
     asshole
    0.62
    言って
    0.59
    ⁹
    0.59
    Calories
    0.57
     Radiology
    0.57
    是在
    0.56
    の名
    0.56
     ピ
    0.55
    POSITIVE LOGITS
    ン
    0.68
    न
    0.66
     én
    0.64
     cél
    0.63
    mán
    0.63
     شئ
    0.63
    ку
    0.63
    ла
    0.61
     básicos
    0.61
     musí
    0.61
    Act Density 0.000%

    No Known Activations