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

    Neuronpedia

    INDEX
    Explanations

    spans of code snippets or conversational text in languages other than English, potentially related to programming or technical topics.

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.82
     limestones
    -0.77
     decathlon
    -0.74
     mortars
    -0.73
     Shaksp
    -0.67
     Galer
    -0.67
     dolomite
    -0.66
     Deuter
    -0.65
     ebony
    -0.65
     craters
    -0.65
    POSITIVE LOGITS
     &___
    0.76
    XmlAccessType
    0.72
    EDEFAULT
    0.66
     ​​
    0.65
     continuant
    0.64
    DOCTYPE
    0.62
    '],
    0.60
    heden
    0.59
    "],
    0.58
    UALLY
    0.58
    Act Density 0.730%

    No Known Activations