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

    Neuronpedia

    INDEX
    Explanations

    variable names and parameters in code

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

    code identifiers and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.44
     ویکی‌پدیا
    -0.42
     himmel
    -0.41
     céu
    -0.41
     automatiques
    -0.41
     Himmel
    -0.40
     auroit
    -0.38
     conmigo
    -0.38
     cielos
    -0.37
     transición
    -0.37
    POSITIVE LOGITS
     iParam
    0.62
     localObject
    0.60
    iLocal
    0.60
    arResult
    0.60
     bParam
    0.56
    RTHOOK
    0.54
    Legături
    0.52
     ErrInvalid
    0.52
    aarrggbb
    0.52
    setVerticalGroup
    0.52
    Act Density 0.024%

    No Known Activations