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

    Neuronpedia

    INDEX
    Explanations

    programming questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mechanically
    -0.06
     ◆
    -0.06
    awa
    -0.06
    _season
    -0.06
    #+#+
    -0.06
    atables
    -0.06
    PERTIES
    -0.06
     Χ
    -0.06
    PYTHON
    -0.06
     pairwise
    -0.06
    POSITIVE LOGITS
    *K
    0.07
     đế
    0.06
     omit
    0.06
     علت
    0.06
    .MESSAGE
    0.06
    /templates
    0.06
     pairs
    0.06
    lemen
    0.06
    Et
    0.06
     BUFFER
    0.06
    Act Density 0.133%

    No Known Activations