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

    Neuronpedia

    INDEX
    Explanations

    specific statistical and numerical relationships and their context in a business or health framework

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

    Followed by "the", "is", or a number

    np_acts-logits-general · gemini-2.0-flash

    common divisor or factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ...
    -0.62
     “...
    -0.58
     "...
    -0.57
      
    -0.53
     (
    -0.53
    ...
    -0.52
     ....
    -0.49
     (...
    -0.47
    ....
    -0.46
     “
    -0.45
    POSITIVE LOGITS
    InitVars
    0.65
    Autoritní
    0.58
     itſelf
    0.47
    ագրություններ
    0.47
     disambiguazione
    0.46
    nodoc
    0.45
     zijne
    0.44
     mijne
    0.43
     uitz
    0.42
    pexpr
    0.42
    Act Density 0.022%

    No Known Activations