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

    Neuronpedia

    INDEX
    Explanations

    pdfminer.six extraction library

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ল
    0.73
     १०
    0.64
    رم
    0.64
    ERTS
    0.61
    اً
    0.60
    Ngoài
    0.60
     zákon
    0.59
    즐
    0.59
     süre
    0.59
    लग
    0.59
    POSITIVE LOGITS
    яна
    0.58
     shining
    0.56
     Needless
    0.55
     tenets
    0.52
    需
    0.52
    stated
    0.52
     meas
    0.52
    k
    0.52
     tulis
    0.51
    sembling
    0.51
    Act Density 0.003%

    No Known Activations