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

    Neuronpedia

    INDEX
    Explanations

    descriptive words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    った
    0.41
    कों
    0.41
    尟
    0.40
    cion
    0.40
    nocześnie
    0.39
     مباشرة
    0.39
    ínio
    0.39
    kowo
    0.38
     أو
    0.38
    ند
    0.38
    POSITIVE LOGITS
     Andy
    0.51
    ुलम
    0.49
    ȟ
    0.49
    ఓ
    0.48
    뿔
    0.48
     pudiera
    0.48
     ROD
    0.48
    uskal
    0.47
    ংকর
    0.45
     getUsersBy
    0.45
    Act Density 0.000%

    No Known Activations