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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting characters in code

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

    code structure separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.57
    dcmtk
    -0.57
    -------------</
    -0.56
    astéroïdes
    -0.52
    FunctionFlags
    -0.51
    HideFlags
    -0.51
    webElementGuid
    -0.50
    crollView
    -0.50
    WriteTagHelper
    -0.48
    tonode
    -0.47
    POSITIVE LOGITS
    UpInside
    0.44
     technique
    0.43
     <<<<<<<<<<<<<<
    0.42
    method
    0.40
    ScopeManager
    0.39
     method
    0.39
    technique
    0.38
    };*/
    0.38
    IndentedString
    0.38
    interview
    0.35
    Act Density 0.039%

    No Known Activations