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

    Neuronpedia

    INDEX
    Explanations

    URLs and HTML formatting, especially within forum-like text.

    oai_token-act-pair · gemini-2.0-flash

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.88
     متعلقه
    -0.85
    __':
    -0.82
    -0.81
    __":
    -0.79
    ."</
    -0.75
     itſelf
    -0.74
    parsedMessage
    -0.74
    ViewImports
    -0.70
     Efq
    -0.69
    POSITIVE LOGITS
     
    0.59
    ATTER
    0.48
    val
    0.46
     Main
    0.45
    OMEN
    0.45
    uker
    0.44
     Gef
    0.44
     Fair
    0.44
    IVAL
    0.44
    s
    0.43
    Act Density 2.327%

    No Known Activations