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

    Neuronpedia

    INDEX
    Explanations

    negations and their implications in discussions

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

    Follows "t" and precedes certain verbs

    np_acts-logits-general · gemini-2.0-flash

    ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cination
    -0.64
     persons
    -0.56
    Cordialement
    -0.53
     Persons
    -0.52
    KommentareTeilen
    -0.50
    ☉
    -0.49
    indeed
    -0.48
    issements
    -0.48
    persons
    -0.48
     nạ
    -0.48
    POSITIVE LOGITS
    ’)
    1.26
    ’.
    1.25
    ’,
    1.21
    ’).
    1.20
    ’:
    1.12
    ’;
    1.08
    ’?
    1.06
    ’”
    1.06
    .’
    1.06
    ”),
    1.05
    Act Density 0.087%

    No Known Activations