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

    Neuronpedia

    INDEX
    Explanations

    evaluative language regarding ethics and usefulness

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

    Positive adjectives

    np_acts-logits-general · gemini-2.0-flash

    positive adjectives followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.07
     Efq
    -1.03
    DeleteBehavior
    -1.00
    URLException
    -1.00
    expandindo
    -1.00
    AddTagHelper
    -0.98
     كومونز
    -0.95
    GEBURTSDATUM
    -0.95
    InjectAttribute
    -0.94
     Himo
    -0.94
    POSITIVE LOGITS
     for
    0.97
     in
    0.68
     to
    0.67
     against
    0.66
     when
    0.62
     if
    0.57
     on
    0.53
     during
    0.53
     at
    0.53
     here
    0.52
    Act Density 0.360%

    No Known Activations