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

    Neuronpedia

    INDEX
    Explanations

    is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்ப
    0.74
    landır
    0.70
     align
    0.63
    iac
    0.61
    dometer
    0.60
     الاح
    0.60
    aim
    0.60
    IDField
    0.60
    mim
    0.60
    ဥ
    0.60
    POSITIVE LOGITS
     может
    1.09
     może
    1.02
     môže
    1.01
     refers
    1.01
     vagy
    1.00
     може
    0.97
    是一种
    0.94
     또는
    0.93
     adalah
    0.92
     möglicherweise
    0.91
    Act Density 0.037%

    No Known Activations