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

    Neuronpedia

    INDEX
    Explanations

    magnitude comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.91
    us
    0.84
    nikiem
    0.82
    szer
    0.80
    ኚ
    0.80
    ત્
    0.79
    um
    0.79
    ן
    0.77
     आयुर्वेदिक
    0.76
    цата
    0.75
    POSITIVE LOGITS
     bioquímica
    1.00
     homeostasis
    0.96
     основные
    0.96
     fates
    0.96
     śred
    0.95
     izgleda
    0.95
     性
    0.93
     ہیں۔
    0.92
    。
    0.91
     زمانہ
    0.91
    Act Density 0.160%

    No Known Activations