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

    Neuronpedia

    INDEX
    Explanations

    Prevention/restriction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .section
    -0.07
    	while
    -0.07
    ารถ
    -0.07
     derivative
    -0.07
    UIKit
    -0.06
     sociology
    -0.06
    .JButton
    -0.06
    .Since
    -0.06
    _Project
    -0.06
     امیر
    -0.06
    POSITIVE LOGITS
    σφα
    0.07
    ूत
    0.07
     Poss
    0.06
    elho
    0.06
    atories
    0.06
     Loving
    0.06
    _proxy
    0.06
     tacos
    0.06
     injuring
    0.06
    +'\
    0.06
    Act Density 0.176%

    No Known Activations