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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and dates

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

    November, December months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     huge
    -0.58
     ruthless
    -0.54
     lazy
    -0.52
     lots
    -0.51
     different
    -0.50
     pretty
    -0.50
     big
    -0.50
     hefty
    -0.49
     pisau
    -0.48
     HUGE
    -0.48
    POSITIVE LOGITS
    ItemBackground
    0.53
     للمعارف
    0.53
    rawDesc
    0.52
     IndexError
    0.49
     columnIndex
    0.49
    évaluateur
    0.47
     bParam
    0.47
     endfor
    0.47
    parsedMessage
    0.45
    UserScript
    0.44
    Act Density 0.239%

    No Known Activations