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

    Neuronpedia

    INDEX
    Explanations

    sequences that indicate comments or documentation in code

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

    Chinese email domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.75
    <unused52>
    -0.71
    [@BOS@]
    -0.70
    <unused3>
    -0.70
    <unused68>
    -0.70
    <unused74>
    -0.70
    <unused43>
    -0.70
    <unused23>
    -0.70
    <unused14>
    -0.70
    <unused16>
    -0.70
    POSITIVE LOGITS
     Tecnología
    0.38
     Garantía
    0.38
     tecnología
    0.38
     nación
    0.38
     Tecn
    0.36
     China
    0.33
     verano
    0.33
     chinoise
    0.33
    China
    0.32
     tecn
    0.32
    Act Density 0.006%

    No Known Activations