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

    Neuronpedia

    INDEX
    Explanations

    epistemology of ones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Goodman
    0.55
     высокая
    0.55
    льзя
    0.55
     давайте
    0.55
     impracticable
    0.54
     NIO
    0.54
    احنا
    0.54
     champagne
    0.53
    ль
    0.53
     Prandtl
    0.53
    POSITIVE LOGITS
    et
    0.84
    opo
    0.66
    eles
    0.65
    나
    0.62
    ari
    0.61
    sir
    0.61
    và
    0.59
    CE
    0.58
    elor
    0.58
    san
    0.58
    Act Density 0.000%

    No Known Activations