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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate simplification or clarification of complex ideas

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

    phrases like "said differently" or "more precisely"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.56
     JpaRepository
    -0.41
     unknownFields
    -0.38
     cref
    -0.38
    FunctionFlags
    -0.37
    HasForeignKey
    -0.36
    tableFuture
    -0.36
    afficheront
    -0.36
    sizeCache
    -0.36
    PMailer
    -0.35
    POSITIVE LOGITS
     فريبيس
    0.72
    Viited
    0.55
    glEnd
    0.52
    0.47
     summary
    0.47
    //-->
    0.45
    لينكات
    0.45
    aarrggbb
    0.45
     SwitchCompat
    0.45
    Conclusie
    0.45
    Act Density 0.068%

    No Known Activations