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

    Neuronpedia

    INDEX
    Explanations

    key transitional or connective words and phrases in the text

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

    words starting with certain prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.83
    الدراسه
    -0.72
    -0.71
     الرياضيه
    -0.70
    الحياه
    -0.66
    parsedMessage
    -0.66
    KommentareTeilen
    -0.66
    niſſe
    -0.65
    SharedCtor
    -0.65
    Tikang
    -0.64
    POSITIVE LOGITS
     silvestre
    0.24
     Lieferung
    0.23
     vreme
    0.23
     Initialized
    0.23
    sigt
    0.23
    SuspendLayout
    0.22
    The
    0.22
    1
    0.21
    lock
    0.21
    ule
    0.21
    Act Density 0.005%

    No Known Activations