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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections in the text

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

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    special characters and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;—
    -0.68
     daß
    -0.67
    faßt
    -0.67
     wherewith
    -0.66
     iż
    -0.55
    dest
    -0.55
    ;++
    -0.54
     ){
    -0.54
     Schluß
    -0.53
     insom
    -0.53
    POSITIVE LOGITS
    .*")]
    0.83
     تضيفلها
    0.68
    NameInMap
    0.65
     []:
    0.65
    Datuak
    0.64
     وتسجيلات
    0.63
     Protección
    0.60
    bigsqcup
    0.59
    setminus
    0.58
     XNUMX
    0.58
    Act Density 0.294%

    No Known Activations