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

    Neuronpedia

    INDEX
    Explanations

    specific instances of emotional highs or focal moments in personal narratives

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

    Following quotations or commas

    np_acts-logits-general · gemini-2.0-flash

    probably, definitely, maybe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     full
    -0.49
    Full
    -0.46
     peł
    -0.45
    ệu
    -0.44
     ${\
    -0.43
    ც
    -0.42
     Full
    -0.42
    FULL
    -0.41
    unzione
    -0.41
    }")]
    -0.41
    POSITIVE LOGITS
    Probably
    0.91
     Probably
    0.84
     prolly
    0.83
    probably
    0.83
     probably
    0.81
    بوابة
    0.81
     наверное
    0.77
    Definitely
    0.77
    maybe
    0.75
    Depends
    0.73
    Act Density 0.115%

    No Known Activations