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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

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

    proper names and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cip
    -0.48
     noqa
    -0.48
    ListItemIcon
    -0.47
    存于互联网档案馆
    -0.45
    Subviews
    -0.45
     comb
    -0.45
     pyp
    -0.45
     deviation
    -0.45
    PathParam
    -0.44
     tip
    -0.44
    POSITIVE LOGITS
     Holden
    1.97
     Wilder
    0.71
     HOLD
    0.66
    ilder
    0.64
    Hold
    0.64
     Opel
    0.57
     dezelve
    0.57
    Holt
    0.54
     helicópter
    0.53
     ouder
    0.52
    Act Density 0.007%

    No Known Activations