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

    Neuronpedia

    INDEX
    Explanations

    your or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是一種
    0.52
     doprav
    0.49
     Tinubu
    0.49
     konzerv
    0.47
     HomeScreen
    0.47
     země
    0.46
    وسي
    0.45
    ស្ថ
    0.45
     controlado
    0.45
    驅
    0.45
    POSITIVE LOGITS
    ड्ड
    0.48
    grad
    0.48
     they
    0.47
     current
    0.46
    Grad
    0.45
     deadlines
    0.45
     topics
    0.44
     brownies
    0.43
     (>
    0.43
    al
    0.43
    Act Density 0.001%

    No Known Activations