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

    Neuronpedia

    INDEX
    Explanations

    special formatting or structure in the text

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

    user prompts

    np_acts-logits-general · gemini-2.5-flash-lite

    long runs of tilde characters (repeated '~' used as a separator/formatting marker).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     dager
    -0.31
     sê
    -0.30
     haz
    -0.29
     Von
    -0.28
    …~
    -0.27
     Electr
    -0.27
     Platz
    -0.27
     Ers
    -0.27
     bog
    -0.27
    hausen
    -0.26
    POSITIVE LOGITS
    Personensuche
    0.77
    存于互联网档案馆
    0.73
     noDo
    0.69
    ंदीखरीदारी
    0.65
     CreateTagHelper
    0.64
    Personendaten
    0.63
    httphttps
    0.62
    évaluateur
    0.61
     Administrativna
    0.60
     '\\;'
    0.60
    Act Density 0.000%

    No Known Activations