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

    Neuronpedia

    INDEX
    Explanations

    Korean character '한'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     basal
    0.80
     forerunner
    0.79
    ಿತು
    0.75
     spite
    0.74
     smelled
    0.73
    に見
    0.71
     predecessor
    0.70
     abstinence
    0.70
    的一切
    0.69
     prevented
    0.68
    POSITIVE LOGITS
    واه
    0.78
    ্সি
    0.77
    м
    0.76
    ін
    0.76
    층
    0.72
    δυ
    0.72
    Agregar
    0.71
    껏
    0.71
    μό
    0.70
    νας
    0.69
    Act Density 0.001%

    No Known Activations