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

    Neuronpedia

    INDEX
    Explanations

    instances where someone has looked for help but hasn't been successful

    oai_token-act-pair · gemini-2.0-flash

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ForRow
    -0.49
     himo
    -0.45
    protoc
    -0.45
    WebVitals
    -0.45
    colgroup
    -0.42
    aarrggbb
    -0.42
     unjustly
    -0.42
    quo
    -0.42
    شاركة
    -0.42
     kasarigan
    -0.42
    POSITIVE LOGITS
     tartalomajánló
    0.73
    copg
    0.66
    #+#
    0.65
    };*/
    0.63
    ilight
    0.63
     كومونز
    0.59
    солю
    0.59
     couldn
    0.58
     verle
    0.57
    érience
    0.54
    Act Density 0.655%

    No Known Activations