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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords that signify method overrides and data handling structures

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

    configure, define, programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.51
     itſelf
    -0.50
     poffible
    -0.49
     houſe
    -0.48
    ſelf
    -0.48
     pleaſure
    -0.48
     fubject
    -0.46
     ſch
    -0.46
     Jefus
    -0.46
     poffe
    -0.45
    POSITIVE LOGITS
     configure
    1.48
     configuring
    0.90
     configured
    0.80
     define
    0.68
     configurar
    0.65
     Configure
    0.64
     autorytatywna
    0.62
     disable
    0.60
    ButtonModule
    0.58
    configure
    0.57
    Act Density 0.001%

    No Known Activations