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

    Neuronpedia

    INDEX
    Explanations

    opening parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دف
    -0.07
    �
    -0.07
    Rule
    -0.07
    disp
    -0.06
     Warranty
    -0.06
     confused
    -0.06
     klim
    -0.06
     Chapters
    -0.06
    _draw
    -0.06
     obvious
    -0.06
    POSITIVE LOGITS
    ([
    0.09
     {[
    0.08
    (([
    0.08
    <[
    0.07
    ([^
    0.07
    /car
    0.07
    ,{
    0.07
    хови
    0.07
    (/*
    0.07
    (({
    0.07
    Act Density 0.008%

    No Known Activations