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

    Neuronpedia

    INDEX
    Explanations

    references to legal or formal parameters and considerations

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

    preceding nouns (curve, metal, scheme, etc.)

    np_acts-logits-general · gemini-2.0-flash

    associated with legal/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.78
     AssemblyVersion
    -0.56
    AddTagHelper
    -0.56
     unknownFields
    -0.52
    @[+][
    -0.51
     supérieures
    -0.50
    ázat
    -0.49
     ***!
    -0.48
     quelli
    -0.48
    RuleContext
    -0.47
    POSITIVE LOGITS
    NUMX
    0.78
     purpoſe
    0.78
    esomeness
    0.74
     myſelf
    0.73
     Chriſt
    0.72
    geführten
    0.69
    lected
    0.68
    LEGGI
    0.68
    urlpatterns
    0.67
     fhort
    0.67
    Act Density 0.416%

    No Known Activations