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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and expressions of enjoyment

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

    possessive pronouns and beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hyrchwyd
    -0.35
    >";
    -0.34
     maestros
    -0.34
     artists
    -0.34
    Lähteet
    -0.33
    argp
    -0.33
    ・・・」
    -0.32
     sukienka
    -0.32
     یافته
    -0.31
    erequisite
    -0.31
    POSITIVE LOGITS
     виправивши
    0.62
     ControllerBase
    0.57
     препратки
    0.50
    levance
    0.50
    phosa
    0.49
    ArgsConstructor
    0.49
     NSCoder
    0.48
    URLException
    0.48
    weetened
    0.43
    httphttps
    0.43
    Act Density 0.005%

    No Known Activations