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

    Neuronpedia

    INDEX
    Explanations

    legal terms and conditions related to agreements and regulations

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

    Time periods or deadlines

    np_acts-logits-general · gemini-2.0-flash

    time periods with exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    -0.46
    س
    -0.44
    啊
    -0.43
    makeText
    -0.43
    ak
    -0.43
    -
    -0.42
    da
    -0.41
     
    -0.41
     vs
    -0.41
     noqa
    -0.41
    POSITIVE LOGITS
     unless
    1.34
    unless
    1.27
     sauf
    1.07
     except
    1.07
    Unless
    1.05
     Unless
    1.02
     kecuali
    1.02
    except
    1.01
     excepting
    0.98
     EXCEPT
    0.96
    Act Density 0.400%

    No Known Activations