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

    Neuronpedia

    INDEX
    Explanations

    negations and their corresponding affirmations in the form of "yes" and "no" responses

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

    yes/no answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasAnnotation
    -0.61
    parsedMessage
    -0.54
    DockStyle
    -0.53
     Bambi
    -0.51
     GenerationType
    -0.51
    AnimationsModule
    -0.51
    قایناق‌لار
    -0.50
    StateList
    -0.49
     TDC
    -0.49
    prite
    -0.49
    POSITIVE LOGITS
    Yes
    0.59
    YES
    0.53
    yes
    0.52
     yes
    0.50
    YesNo
    0.48
     Yes
    0.47
     YES
    0.46
    是的
    0.44
    yep
    0.41
     oui
    0.40
    Act Density 0.042%

    No Known Activations