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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing desire or necessity

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

    if desired, if necessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kra
    -0.31
    Personendaten
    -0.30
     Rub
    -0.29
     source
    -0.29
    rift
    -0.29
    zyna
    -0.29
     major
    -0.28
    JPanel
    -0.28
    件
    -0.28
    ⓘ
    -0.28
    POSITIVE LOGITS
    السكان
    0.65
     فريبيس
    0.63
     الحره
    0.63
     تضيفلها
    0.60
    éraires
    0.56
    MemoryWarning
    0.53
    0.53
    UnsafeEnabled
    0.52
    expandindo
    0.51
    IsMutable
    0.51
    Act Density 0.103%

    No Known Activations