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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and data formatting within structured text or code

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

    code syntax punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.05
     ſind
    -0.69
    Personendaten
    -0.69
     laſſen
    -0.68
    niſſe
    -0.68
    iſchen
    -0.67
     müſſen
    -0.67
     iſt
    -0.65
    majánló
    -0.63
     Geiſt
    -0.63
    POSITIVE LOGITS
     וב
    0.52
    =
    0.47
     وال
    0.45
    (
    0.44
     وك
    0.44
     כשה
    0.43
     מל
    0.43
     וה
    0.40
     כש
    0.40
     שב
    0.37
    Act Density 0.292%

    No Known Activations