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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology associated with data types and measurements in a mathematical or programming context

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

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.79
     CURIAM
    -0.70
    ControllerAdvice
    -0.69
    momix
    -0.62
    URBANA
    -0.61
    httphttps
    -0.61
    ſcher
    -0.61
     kasarigan
    -0.61
    iſen
    -0.60
    migrationBuilder
    -0.59
    POSITIVE LOGITS
    ↵↵
    0.32
    ArrowToggle
    0.30
     gainera
    0.29
    da
    0.29
    char
    0.28
    so
    0.27
    son
    0.27
    good
    0.26
    va
    0.26
    One
    0.26
    Act Density 0.078%

    No Known Activations