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

    Neuronpedia

    INDEX
    Explanations

    technical details related to scientific studies and methodologies

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

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.61
    CodeAttribute
    -0.55
    InputBorder
    -0.52
    MemoryWarning
    -0.51
    jenige
    -0.49
     Einfluß
    -0.49
     רבים
    -0.47
    Datuak
    -0.47
    ânsito
    -0.47
    swire
    -0.46
    POSITIVE LOGITS
     three
    0.61
     four
    0.57
    three
    0.55
    ArrowToggle
    0.51
    Three
    0.47
     Three
    0.47
     five
    0.47
    三個
    0.47
    三个
    0.46
     CreateTagHelper
    0.44
    Act Density 0.529%

    No Known Activations