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

    Neuronpedia

    INDEX
    Explanations

    technical terms and components related to API and authentication processes

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

    jenkins build status or credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.41
     béton
    -0.32
     jorden
    -0.31
    documented
    -0.31
     humanidade
    -0.30
    tekend
    -0.30
     polícia
    -0.30
     inmedi
    -0.29
     DOUBLE
    -0.28
    ArrowToggle
    -0.28
    POSITIVE LOGITS
    wicket
    0.75
    parsedMessage
    0.65
    IsContent
    0.56
    انيف
    0.54
     nahilalakip
    0.54
    urlpatterns
    0.52
    ieteur
    0.52
    qtype
    0.50
    RTLU
    0.50
    RTEX
    0.48
    Act Density 0.002%

    No Known Activations