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

    Neuronpedia

    INDEX
    Explanations

    code structure separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lytres
    0.42
    닳
    0.41
     увла
    0.41
    }$-(
    0.39
     картину
    0.39
    piej
    0.39
    Callories
    0.38
    Strafpunkte
    0.38
    glRaster
    0.38
     乳
    0.38
    POSITIVE LOGITS
     a
    0.60
     p
    0.58
    _
    0.57
     n
    0.54
     that
    0.54
     u
    0.53
     is
    0.51
     was
    0.51
     A
    0.51
    is
    0.50
    Act Density 0.187%

    No Known Activations