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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to decoding and data handling

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

    Code related to decoding or breaking

    np_acts-logits-general · gemini-2.0-flash

    decoding structured data with switch statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.88
     betweenstory
    -0.86
     '\\;'
    -0.76
    __':
    -0.73
    setVerticalGroup
    -0.72
     yyr
    -0.72
     mergeFrom
    -0.72
    sidemargin
    -0.70
    ⓧ
    -0.69
    estacks
    -0.69
    POSITIVE LOGITS
    WireFormatLite
    0.69
    ::
    0.54
     ::
    0.42
     Moffat
    0.37
    ->
    0.37
    اظ
    0.35
    ()->
    0.35
    (_
    0.35
     alko
    0.34
     _
    0.33
    Act Density 0.024%

    No Known Activations