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

    Neuronpedia

    INDEX
    Explanations

    references to legal claims and courtroom proceedings

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

    Actions of physical or verbal rejection

    np_acts-logits-general · gemini-2.0-flash

    actions of attack or rejection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     istrinya
    -0.65
     ब्रेकडाउन
    -0.60
     Administrativna
    -0.58
     الرياضيه
    -0.57
     resourceCulture
    -0.52
    Билгалдахарш
    -0.52
     noDo
    -0.50
    Autoritní
    -0.47
     civilian
    -0.45
    UnusedPrivate
    -0.45
    POSITIVE LOGITS
     chồng
    0.50
    丈夫
    0.50
    老公
    0.48
     Snape
    0.47
    oppa
    0.47
    izr
    0.47
     Tractor
    0.46
     Verstappen
    0.46
     Boeing
    0.46
     Fossil
    0.46
    Act Density 5.023%

    No Known Activations