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

    Neuronpedia

    INDEX
    Explanations

    the letter 'S' and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "s" as a suffix or part of non-English words

    np_acts-logits-general · gemini-2.0-flash

    starts with 's'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.74
    IsMutable
    -0.61
    PyExc
    -0.58
     resourceCulture
    -0.54
    XmlAccessType
    -0.54
     yields
    -0.52
    IndentedString
    -0.50
    fjspx
    -0.50
    Enllaces
    -0.49
    /***/
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.72
    躇
    0.64
     '\\;'
    0.54
    atan
    0.49
    layer
    0.48
    ATAN
    0.48
    윗
    0.47
    usan
    0.46
    mile
    0.46
    tan
    0.45
    Act Density 0.217%

    No Known Activations