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

    Neuronpedia

    INDEX
    Explanations

    underscore-prefixed variables or functions in code

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

    underscore-prefixed identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.77
    IntoConstraints
    -0.75
    IsContent
    -0.75
    featureID
    -0.71
    rrggbb
    -0.66
    SequentialGroup
    -0.65
    AnchorTagHelper
    -0.64
    tagext
    -0.63
    Hozzáférés
    -0.60
    URLException
    -0.60
    POSITIVE LOGITS
     _
    0.67
    =_
    0.65
    ::_
    0.59
    (_
    0.56
    [_
    0.56
     *_
    0.55
    ._
    0.55
     '_
    0.54
     "_
    0.54
     (_
    0.54
    Act Density 0.066%

    No Known Activations