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

    Neuronpedia

    INDEX
    Explanations

    titles and positions of authority within organizations

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

    Title or position of a person

    np_acts-logits-general · gemini-2.0-flash

    leadership titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.58
     Мексичка
    -0.55
    MERCE
    -0.54
    PyExc
    -0.53
    toHaveBeenCalled
    -0.52
    üchte
    -0.50
    akkan
    -0.50
     Taktlose
    -0.49
     quantities
    -0.49
     Wiki
    -0.48
    POSITIVE LOGITS
     emeritus
    0.78
     Emeritus
    0.67
     designate
    0.66
     rospy
    0.65
     AssemblyTitle
    0.63
     jScrollPane
    0.63
    StoryboardSegue
    0.61
    を務
    0.60
    hely
    0.60
    hips
    0.60
    Act Density 0.371%

    No Known Activations