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

    Neuronpedia

    INDEX
    Explanations

    names of people and organizations

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

    after capitalized abbreviations/initials

    np_acts-logits-general · gemini-2.0-flash

    names with following suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ranean
    -0.55
     fato
    -0.53
     CreateTagHelper
    -0.48
     base
    -0.47
    rrggbb
    -0.45
     berbeda
    -0.45
     favor
    -0.44
    Reese
    -0.44
     banda
    -0.44
     costos
    -0.44
    POSITIVE LOGITS
     Efq
    1.04
     Forumite
    0.84
     Majefty
    0.81
    0.80
     myſelf
    0.79
     Anſ
    0.78
     RSSSF
    0.75
     Conſ
    0.74
     Diſ
    0.72
     ་་
    0.72
    Act Density 0.193%

    No Known Activations