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

    Neuronpedia

    INDEX
    Explanations

    numbers, codes, and tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Smo
    -0.71
     Pedro
    -0.69
    archer
    -0.68
     mare
    -0.67
     fug
    -0.67
    ileri
    -0.66
     Sophia
    -0.66
     пят
    -0.65
     LATE
    -0.65
     رو
    -0.64
    POSITIVE LOGITS
     enige
    0.70
    umpulan
    0.69
     Pollack
    0.66
     dimensionality
    0.66
    zty
    0.65
    Bedroom
    0.64
    뱅
    0.64
    Guerra
    0.63
     ruling
    0.63
    Zn
    0.62
    Act Density 0.074%

    No Known Activations