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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing specificity or particularity

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

    particular instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spolu
    -0.33
     esquecer
    -0.33
    yonel
    -0.31
    cookieParser
    -0.31
    and
    -0.30
     además
    -0.30
    Inspection
    -0.30
     olvidar
    -0.30
     combined
    -0.29
     régal
    -0.28
    POSITIVE LOGITS
     particolari
    0.88
    particular
    0.88
     particular
    0.88
     Particular
    0.87
     bepaalde
    0.84
    Particular
    0.84
    特定
    0.81
    Certain
    0.81
     PARTICULAR
    0.81
     Certain
    0.80
    Act Density 0.037%

    No Known Activations