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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ্তা
    -0.07
     clare
    -0.07
     newspaper
    -0.07
     mè
    -0.07
     trip
    -0.07
     skyscr
    -0.07
     minimum
    -0.07
     міс
    -0.07
     cen
    -0.07
    لية
    -0.07
    POSITIVE LOGITS
    Tolerance
    0.10
     intolerance
    0.10
     tolerance
    0.09
     tolerated
    0.09
     Максим
    0.09
     parano
    0.09
     incompet
    0.09
    luiten
    0.09
    |max
    0.09
    /<?
    0.09
    Act Density 0.021%

    No Known Activations