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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of doubt or concern

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

    if, whether, what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RequestMapping
    -0.38
     становника
    -0.31
     capot
    -0.30
     perhaps
    -0.29
    ArrowToggle
    -0.29
     cita
    -0.29
    ？
    -0.28
     ActivatedRoute
    -0.28
    \,.
    -0.28
    posób
    -0.28
    POSITIVE LOGITS
    MemoryWarning
    0.66
     betweenstory
    0.60
     maș
    0.58
     Waray
    0.57
    DIPSETTING
    0.54
     فريبيس
    0.51
     mergeFrom
    0.50
    rrggbb
    0.50
    parsedMessage
    0.50
    OrBuilder
    0.49
    Act Density 0.017%

    No Known Activations