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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax elements in programming languages

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

    code and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.62
    Personendaten
    -0.61
    AnchorStyles
    -0.61
     tartalomajánló
    -0.60
    AddTagHelper
    -0.60
    InputBorder
    -0.59
    脚注の使い方
    -0.57
    tagHelperRunner
    -0.57
     Infór
    -0.57
     GenerationType
    -0.56
    POSITIVE LOGITS
    varargin
    0.45
    ftagPool
    0.44
    <bos>
    0.44
    TheReal
    0.36
     Roskov
    0.35
     typelib
    0.35
     TextAppearance
    0.34
     Mat
    0.31
    intă
    0.31
     Skip
    0.30
    Act Density 0.006%

    No Known Activations