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

    Neuronpedia

    INDEX
    Explanations

    DEAL DISCOUNT offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     व्यवस्थित
    0.48
     மேற்கொள்ள
    0.41
    运用
    0.39
    cusson
    0.39
    有一些
    0.38
    tson
    0.37
    他不
    0.37
    jec
    0.37
    थिक
    0.37
    aneous
    0.36
    POSITIVE LOGITS
    瓜
    0.40
    ਮ
    0.39
     DISCOUNT
    0.38
    haba
    0.38
     அப்பா
    0.36
     DEAL
    0.36
    脫
    0.36
    Deal
    0.36
     '''
    0.35
     затра
    0.35
    Act Density 0.000%

    No Known Activations