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

    Neuronpedia

    INDEX
    Explanations

    technical terminologies and instances of guidance for creating or substituting products

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

    about preference or choice

    np_acts-logits-general · gemini-2.0-flash

    making a choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onViewCreated
    -0.64
     الدولى
    -0.60
    MemoryWarning
    -0.60
     ProtoMessage
    -0.56
    setArguments
    -0.56
    setVerticalGroup
    -0.55
     MotionEvent
    -0.53
     velkommen
    -0.52
     numberOfRows
    -0.51
    stateProvider
    -0.51
    POSITIVE LOGITS
     choice
    1.12
     Choice
    1.06
     choix
    1.01
    Choosing
    1.00
    choice
    1.00
    Choice
    0.99
     choices
    0.99
    chosen
    0.97
     choosing
    0.97
     chosen
    0.95
    Act Density 0.697%

    No Known Activations