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

    Neuronpedia

    INDEX
    Explanations

    definitions and syntax related to programming constructs in a technical context

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

    Bitwise AND/OR operations and masks

    np_acts-logits-general · gemini-2.0-flash

    bitwise operations with mask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +"/"+
    -0.58
     namanya
    -0.55
    +".
    -0.55
     Abou
    -0.51
    nani
    -0.49
     Names
    -0.49
    zeß
    -0.48
     '\\;'
    -0.48
    ]='\
    -0.47
     gian
    -0.47
    POSITIVE LOGITS
     bit
    1.25
     bits
    1.14
    bit
    1.11
    bits
    1.09
     mask
    1.09
     BIT
    1.08
     Bit
    1.07
    Bit
    1.06
    mask
    1.04
     Bits
    1.02
    Act Density 0.766%

    No Known Activations