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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sleeper
    -0.09
     tuh
    -0.08
     materially
    -0.08
     astrolog
    -0.08
     tese
    -0.08
     paa
    -0.08
    कर्ता
    -0.08
     ite
    -0.08
     materiali
    -0.08
     tehn
    -0.08
    POSITIVE LOGITS
    .opts
    0.08
     electroph
    0.08
    了一
    0.08
     hoping
    0.08
     Elect
    0.08
     hopes
    0.08
    Publication
    0.08
     Однако
    0.07
    éli
    0.07
     درست
    0.07
    Act Density 0.187%

    No Known Activations