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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and technical terms related to specific subjects

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

    eukaryotic, ubuntu, SOA, 0xffff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McClure
    -0.47
     Scrooge
    -0.44
    ordes
    -0.43
    gö
    -0.43
    roides
    -0.42
     coll
    -0.42
    Xiao
    -0.42
     cassa
    -0.42
     base
    -0.41
     Huo
    -0.41
    POSITIVE LOGITS
     Rowan
    0.98
    Rowan
    0.97
     Arun
    0.81
    Arun
    0.76
     kasarigan
    0.73
     Majefty
    0.69
    算
    0.68
     disponibilités
    0.62
     onAnimation
    0.62
    cak
    0.60
    Act Density 0.010%

    No Known Activations