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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming functions and parameters in APIs

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

    Code or text mentioning a boolean value

    np_acts-logits-general · gemini-2.0-flash

    boolean value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     setContent
    -0.49
     efficacement
    -0.44
     ordinaires
    -0.43
     milliers
    -0.43
     eventName
    -0.43
     posX
    -0.42
     misfortune
    -0.42
    ValueStyle
    -0.42
     centaines
    -0.41
     ordinaire
    -0.41
    POSITIVE LOGITS
     use
    0.94
     force
    0.92
     allow
    0.89
     Force
    0.86
     show
    0.83
    force
    0.83
     Show
    0.83
     FORCE
    0.82
     keep
    0.81
     مرئيه
    0.80
    Act Density 0.425%

    No Known Activations