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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts emphasizing exclusivity or limitation

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

    only or solely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.52
     للاسماء
    -0.49
    DrawerToggle
    -0.47
    ⓧ
    -0.45
     subtropical
    -0.38
    JMenuBar
    -0.38
    tagext
    -0.36
     cascada
    -0.36
    WindowConstants
    -0.36
    ValueGenerated
    -0.35
    POSITIVE LOGITS
     only
    0.90
    only
    0.90
     ONLY
    0.86
     Only
    0.85
    Only
    0.85
    ONLY
    0.84
     alleen
    0.75
     uniquement
    0.75
     alone
    0.73
     только
    0.72
    Act Density 0.342%

    No Known Activations