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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experience and information, particularly regarding the subject's background and identity

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

    Follows first-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.69
    msgSender
    -0.63
    rillas
    -0.63
    存于互联网档案馆
    -0.62
     ostensibly
    -0.62
    ].)
    -0.60
     esche
    -0.59
    ilha
    -0.57
    رشف
    -0.57
    skrä
    -0.56
    POSITIVE LOGITS
     Apabila
    0.65
    osoever
    0.61
     mempunyai
    0.59
     Hence
    0.56
     mainly
    0.55
    Hence
    0.54
     habitants
    0.54
     realice
    0.53
     Moreover
    0.52
     prouve
    0.52
    Act Density 0.307%

    No Known Activations