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

    Neuronpedia

    INDEX
    Explanations

    titles and subtitles indicated by a colon

    oai_token-act-pair · gemini-2.0-flash

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.60
    Santis
    -0.58
    يكب
    -0.58
    elemField
    -0.57
     autorytatywna
    -0.55
    ContentAsync
    -0.54
    ########.
    -0.52
    Yeet
    -0.52
    ès
    -0.51
     Geraadpleegd
    -0.50
    POSITIVE LOGITS
    __":
    0.86
    __':
    0.70
    rxjs
    0.63
     nemlig
    0.61
    ">:
    0.58
    __":
    0.57
    []):
    0.54
     namelijk
    0.51
     ***!
    0.50
     jspb
    0.48
    Act Density 1.715%

    No Known Activations