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

    Neuronpedia

    INDEX
    Explanations

    standard output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    9
    0.76
    ↵
    0.62
    8
    0.62
    ول
    0.61
    0
    0.59
    ，
    0.58
     vendre
    0.56
     точки
    0.56
     Entwicklung
    0.55
    ية
    0.54
    POSITIVE LOGITS
    ቈ
    0.63
    ajā
    0.59
    ides
    0.57
    㗽
    0.57
    冭
    0.57
    セイ
    0.57
    ad
    0.57
    त
    0.56
    ಲ್ಲು
    0.55
    エス
    0.55
    Act Density 0.019%

    No Known Activations