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

    Neuronpedia

    INDEX
    Explanations

    definitions and structures related to programming or technical specifications

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

    Bitwise operations and data manipulation

    np_acts-logits-general · gemini-2.0-flash

    bitwise operations: shift, mask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pedal
    -0.52
     foot
    -0.47
    elung
    -0.45
     gas
    -0.44
     hoof
    -0.43
    RectF
    -0.42
     throttle
    -0.42
    ก
    -0.42
    매
    -0.41
     Tal
    -0.40
    POSITIVE LOGITS
     bit
    1.04
    bit
    0.95
     Bit
    0.93
    bits
    0.91
    Bit
    0.91
     Bits
    0.91
     intptr
    0.88
    Bits
    0.86
     BIT
    0.86
     bits
    0.86
    Act Density 1.187%

    No Known Activations