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

    Neuronpedia

    INDEX
    Explanations

    method calls and function signatures in programming code

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

    code delimiters and programming structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.86
    aarrggbb
    -0.73
    MessageTagHelper
    -0.58
     onAnimation
    -0.56
     TestBed
    -0.56
     hyg
    -0.55
     retVal
    -0.55
    なりに
    -0.54
    قایناق‌لار
    -0.54
    AnchorTagHelper
    -0.53
    POSITIVE LOGITS
     trône
    0.52
     vœ
    0.48
     commandement
    0.47
     orientación
    0.41
     élu
    0.40
     autorización
    0.39
     espoir
    0.39
     autorité
    0.38
     autoridad
    0.37
     panoramique
    0.36
    Act Density 0.018%

    No Known Activations