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

    Neuronpedia

    INDEX
    Explanations

    terms related to assessment and evaluation processes

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

    Following "determine" or "determination"

    np_acts-logits-general · gemini-2.0-flash

    ascertaining facts or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.71
     “
    -0.64
     F
    -0.59
     I
    -0.58
    arache
    -0.57
     van
    -0.55
     Red
    -0.54
    light
    -0.53
      
    -0.53
    words
    -0.53
    POSITIVE LOGITS
     auffi
    1.09
     Majefty
    1.07
     myſelf
    1.04
     Reſ
    1.04
     purpoſe
    1.04
     greateſt
    1.02
     Efq
    1.02
     faſt
    1.02
    parsedMessage
    0.99
    /**
    0.98
    Act Density 0.095%

    No Known Activations