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

    Neuronpedia

    INDEX
    Explanations

    patterns related to iterative processes and their components in mathematical contexts

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

    names and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.71
    ckså
    -0.55
     varandra
    -0.52
    Hentet
    -0.51
    AISSEE
    -0.50
     itſelf
    -0.49
    ніципалі
    -0.48
     autorytatywna
    -0.48
     kasarigan
    -0.47
    HtmlAttribute
    -0.46
    POSITIVE LOGITS
    Viitteet
    0.43
    fertig
    0.43
    Билгалдахарш
    0.41
     Bradshaw
    0.41
     Taylor
    0.41
    CHREIBUNG
    0.41
     case
    0.41
     Keller
    0.40
    LookAnd
    0.40
    теристика
    0.39
    Act Density 0.056%

    No Known Activations