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

    Neuronpedia

    INDEX
    Explanations

    numerals and their contextual usage within textual information

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

    Numbers enclosed in parentheses

    np_acts-logits-general · gemini-2.0-flash

    percentages and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نتاج
    -0.57
    InitVars
    -0.54
    zbęd
    -0.52
    InputModule
    -0.51
     Sist
    -0.51
    ertal
    -0.49
    RunWith
    -0.49
    र्न
    -0.49
     rel
    -0.48
    ыгана
    -0.47
    POSITIVE LOGITS
    0.74
     propOrder
    0.72
    writeFieldEnd
    0.69
     createSlice
    0.67
    expandindo
    0.66
    copg
    0.61
     resourceCulture
    0.51
    tagHelperRunner
    0.50
    󠁣
    0.50
     '\\;'
    0.50
    Act Density 0.491%

    No Known Activations