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

    Neuronpedia

    INDEX
    Explanations

    sums and series

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坐
    -0.08
     শুক
    -0.08
    Callbacks
    -0.08
    (encoded
    -0.08
     tink
    -0.07
     pret
    -0.07
     schade
    -0.07
     messenger
    -0.07
     Infinity
    -0.07
    /apps
    -0.07
    POSITIVE LOGITS
     overlapping
    0.11
     consecutive
    0.10
     پنج
    0.10
     paleo
    0.10
     neighboring
    0.10
     contiguous
    0.10
    lapping
    0.09
     nine
    0.09
     overlap
    0.09
     Sixth
    0.09
    Act Density 0.026%

    No Known Activations