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

    Neuronpedia

    INDEX
    Explanations

    sections discussing experimental results and their implications

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    code endings and list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Let
    -0.59
     Lets
    -0.58
     Sometimes
    -0.56
     lets
    -0.55
     Anything
    -0.55
    Sometimes
    -0.55
     every
    -0.55
    Let
    -0.54
     anything
    -0.53
     Natürlich
    -0.53
    POSITIVE LOGITS
    Consistent
    0.93
     Consistent
    0.92
     Interestingly
    0.88
     الحره
    0.87
    urlpatterns
    0.84
    Interestingly
    0.83
    tagHelperRunner
    0.82
     interestingly
    0.79
     Significantly
    0.79
     Surprisingly
    0.79
    Act Density 1.364%

    No Known Activations