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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to "what" and "how."

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

    "What" followed by a question

    np_acts-logits-general · gemini-2.0-flash

    what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.68
     jScrollPane
    -0.66
    TemporalType
    -0.61
     ComVisible
    -0.61
     Normdatei
    -0.61
     AspNetCore
    -0.60
     onOptions
    -0.59
     '\\;'
    -0.59
     utafitiHapana
    -0.59
     BoxDecoration
    -0.58
    POSITIVE LOGITS
     Happens
    0.57
     такое
    0.57
    happens
    0.54
     händer
    0.53
    attendre
    0.52
    vece
    0.52
     Exactly
    0.52
     causes
    0.52
     differenza
    0.50
    ']));
    0.49
    Act Density 0.121%

    No Known Activations