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

    Neuronpedia

    INDEX
    Explanations

    technical formatting elements and parameters in code or markup

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adopted
    -0.43
    worthy
    -0.42
     Schmid
    -0.42
     succeeding
    -0.41
    si
    -0.41
    lamiento
    -0.40
    ürtel
    -0.39
    ur
    -0.39
    related
    -0.39
     accepted
    -0.38
    POSITIVE LOGITS
    ionales
    0.71
    tagHelperRunner
    0.63
    出版年
    0.60
    Хьажоргаш
    0.60
    hematics
    0.59
     שוליים
    0.54
    oneofs
    0.54
     estekak
    0.52
     Roskov
    0.51
     Signalez
    0.50
    Act Density 0.001%

    No Known Activations