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

    Neuronpedia

    INDEX
    Explanations

    coding-related functions and operations involving strings and whitespace manipulation

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

    trimming excess or whitespace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.55
    AnchorTagHelper
    -0.53
     NSCoder
    -0.51
    IsMutable
    -0.50
    featureID
    -0.47
    yntaxException
    -0.45
     informée
    -0.44
    Geplaatst
    -0.43
    rrggbb
    -0.42
    ThroughAttribute
    -0.42
    POSITIVE LOGITS
     superfluous
    0.79
     excess
    0.77
     unnecessary
    0.74
     trim
    0.69
    trim
    0.69
    excess
    0.68
     unwanted
    0.67
     excessive
    0.66
     extraneous
    0.66
     Excess
    0.64
    Act Density 0.036%

    No Known Activations