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

    Neuronpedia

    INDEX
    Explanations

    github pages

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of GitHub Pages hosting (e.g. “github.io,” “Pages,” Jekyll site references).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ir
    -0.06
     duk
    -0.06
     Depending
    -0.06
    енью
    -0.06
    Santa
    -0.06
    usive
    -0.06
     gameplay
    -0.06
     Συν
    -0.06
    oret
    -0.06
     hence
    -0.06
    POSITIVE LOGITS
    Limit
    0.07
     stood
    0.07
    -nav
    0.07
    third
    0.07
    (($
    0.07
     Би
    0.07
     торгів
    0.06
    //------------------------------------------------
    0.06
     Oliv
    0.06
     tipo
    0.06
    Act Density 0.005%

    No Known Activations