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

    Neuronpedia

    INDEX
    Explanations

    informational purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     only
    1.36
    only
    1.06
     ONLY
    1.03
     Only
    1.02
     somente
    0.94
    Only
    0.92
    ONLY
    0.90
    เพียง
    0.87
     advice
    0.86
     কেবলমাত্র
    0.86
    POSITIVE LOGITS
    푎
    0.86
    Caractéristiques
    0.84
     کاروبار
    0.82
    Hasil
    0.80
    㩽
    0.80
    斜
    0.80
    fNil
    0.79
    ഞ്ഞു
    0.79
    0.79
    Roasted
    0.79
    Act Density 0.018%

    No Known Activations