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

    Neuronpedia

    INDEX
    Explanations

    references to web links and online sources

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    ‘Why’ and ‘how’ statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.03
    ViewFeatures
    -0.77
     thereto
    -0.74
    abestanden
    -0.69
    TagHelper
    -0.68
    :✨
    -0.67
     CHAPITRE
    -0.66
     Roskov
    -0.65
    SPATH
    -0.64
    AnchorStyles
    -0.63
    POSITIVE LOGITS
     ‘
    0.80
     Why
    0.80
     How
    0.75
     '
    0.75
    ‘
    0.72
    Why
    0.71
    How
    0.69
    ANALYSIS
    0.68
     how
    0.68
     “
    0.67
    Act Density 0.085%

    No Known Activations