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

    Neuronpedia

    INDEX
    Explanations

    structured data and parameters in code or syntax formats

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

    Values and IDs in data structures

    np_acts-logits-general · gemini-2.0-flash

    id/value attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    исленность
    -0.49
     {{\
    -0.47
     lenker
    -0.46
     [['
    -0.43
     NUKAT
    -0.43
    　　【
    -0.42
    νι
    -0.42
     Grüsse
    -0.42
    λλην
    -0.42
    Джерела
    -0.41
    POSITIVE LOGITS
    VersionUID
    0.92
     nineteen
    0.79
     sixty
    0.78
     forty
    0.78
     eighty
    0.77
    BeginContext
    0.75
     seventy
    0.74
     nine
    0.73
     
    0.73
    awtextra
    0.72
    Act Density 0.901%

    No Known Activations