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

    Neuronpedia

    INDEX
    Explanations

    specific character encodings, particularly variations of UTF

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

    utf-8 character encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.52
    tinyos
    -0.47
    StateToProps
    -0.47
     RouterModule
    -0.46
    consider
    -0.45
     Alamos
    -0.44
    stination
    -0.44
     Allociné
    -0.43
    azgo
    -0.42
    évaluateur
    -0.42
    POSITIVE LOGITS
    utf
    3.11
     utf
    2.02
    UTF
    1.80
     UTF
    1.58
    Utf
    1.52
     Utf
    1.28
    StandardCharsets
    0.75
     unicode
    0.61
    csrf
    0.56
    ttf
    0.56
    Act Density 0.005%

    No Known Activations