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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diz
    -0.07
     Thirty
    -0.07
    /mark
    -0.07
    off
    -0.07
     derivative
    -0.06
     defense
    -0.06
    ato
    -0.06
    igth
    -0.06
     scr
    -0.06
    овер
    -0.06
    POSITIVE LOGITS
    pecia
    0.07
    .jsx
    0.06
    .insertBefore
    0.06
    Web
    0.06
     jos
    0.06
     Whole
    0.06
    ﾏ
    0.06
    �
    0.06
    .times
    0.06
    =*
    0.06
    Act Density 0.003%

    No Known Activations