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

    Neuronpedia

    INDEX
    Explanations

    LaTeX-style commands and syntax used for formatting mathematical expressions

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

    mathematical notation and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.54
     Normdatei
    -0.53
    wiſe
    -0.42
     fubject
    -0.42
    Cyfeiriadau
    -0.41
     ſch
    -0.41
     diſt
    -0.41
     مشين
    -0.40
    Predecesor
    -0.39
     ligiloj
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.56
    endphp
    0.48
    einf
    0.47
    didSet
    0.46
     cref
    0.45
     ::=
    0.45
    setViewportView
    0.45
     StatefulWidget
    0.45
     StatelessWidget
    0.43
    Danke
    0.41
    Act Density 0.008%

    No Known Activations