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

    Neuronpedia

    INDEX
    Explanations

    various languages, specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.67
    ,'
    0.59
    lara
    0.59
    nach
    0.55
    lig
    0.53
    izare
    0.53
    )}
    0.52
    ฤษ
    0.51
    lard
    0.50
     attaches
    0.49
    POSITIVE LOGITS
    ン
    0.69
    ラ
    0.64
    ぁ
    0.63
    یکی
    0.62
    あ
    0.62
    ネック
    0.61
    티브
    0.61
    Công
    0.61
    ன்ன
    0.59
    اشی
    0.59
    Act Density 0.000%

    No Known Activations