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

    Neuronpedia

    INDEX
    Explanations

    structured iterative processes and data manipulation

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

    Preceding "next," "another," or verb "rewritten"

    np_acts-logits-general · gemini-2.0-flash

    next item or repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CodedInputStream
    -0.40
    Affirmed
    -0.39
     Durability
    -0.38
     durability
    -0.37
     Schub
    -0.36
     contextLoads
    -0.34
     Gesang
    -0.34
     aba
    -0.34
     bertanggung
    -0.33
    Durability
    -0.33
    POSITIVE LOGITS
     للاسماء
    0.68
     EconPapers
    0.67
     Италијани
    0.62
     '\\;'
    0.60
     defaultstate
    0.59
     nahilalakip
    0.54
    Tikang
    0.53
     newBuilder
    0.52
     ویکی‌پدی
    0.52
    DockStyle
    0.51
    Act Density 0.513%

    No Known Activations