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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of statements

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

    email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSprite
    -0.49
    httphttps
    -0.44
     enough
    -0.43
    jména
    -0.42
     arşivlendi
    -0.42
     μὲν
    -0.42
    urka
    -0.42
    ädie
    -0.42
    ického
    -0.41
    Betyg
    -0.41
    POSITIVE LOGITS
    .</
    0.59
    .
    0.57
    .}\
    0.54
     "*.
    0.53
    .'.
    0.53
    .].
    0.53
    ########.
    0.52
    sidemargin
    0.50
    */].
    0.49
    .*")]
    0.49
    Act Density 0.008%

    No Known Activations