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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to rules and syntax

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.73
     שוליים
    -0.68
    httphttps
    -0.66
     виправивши
    -0.65
    enumi
    -0.58
    antMatchers
    -0.57
    omiast
    -0.57
     esternos
    -0.56
     defaultstate
    -0.56
    //
    -0.54
    POSITIVE LOGITS
    :✨
    0.60
    adpleegd
    0.56
     *>(
    0.50
    ❷
    0.48
    dani
    0.47
    méno
    0.46
    Version
    0.46
    ">//
    0.46
     hàm
    0.46
    loc
    0.46
    Act Density 4.632%

    No Known Activations