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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron detects terms and punctuation typical of software copyright and license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     startIndex
    -0.07
     му
    -0.07
    mkdir
    -0.07
     trabalho
    -0.07
     fills
    -0.06
     south
    -0.06
     além
    -0.06
     SOUTH
    -0.06
     busty
    -0.06
    esine
    -0.06
    POSITIVE LOGITS
     폭
    0.07
    мерик
    0.06
     Toilet
    0.06
     memorable
    0.06
     Carb
    0.06
     disagree
    0.06
    /comment
    0.06
    .rm
    0.06
    利
    0.06
    香蕉
    0.06
    Act Density 0.002%

    No Known Activations