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

    Neuronpedia

    INDEX
    Explanations

    references to specific items, titles, and proper nouns

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

    before naturally, schools, computers, stars, diapers, viruses

    np_acts-logits-general · gemini-2.0-flash

    dogs, schools, stars, diapers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISODE
    -0.58
    atural
    -0.50
    ElementException
    -0.50
    perature
    -0.48
     Their
    -0.46
     Barbuda
    -0.45
    ManagedBean
    -0.45
    JSONException
    -0.45
     mute
    -0.45
    RTLE
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.71
    ⎨
    0.65
     useStyles
    0.64
     تانيه
    0.61
    ']))
    0.60
    ScopeManager
    0.59
    tagHelperRunner
    0.59
    (!__
    0.57
    #+#
    0.56
    tonsoft
    0.56
    Act Density 0.513%

    No Known Activations