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

    Neuronpedia

    INDEX
    Explanations

    demographic data and statistical information related to health and population

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

    percent amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yaşad
    -0.42
    antaine
    -0.42
    きます
    -0.41
     obviously
    -0.39
     clearly
    -0.39
     Signalez
    -0.38
    obviously
    -0.36
     apparently
    -0.36
    MemoryWarning
    -0.36
     Verständ
    -0.35
    POSITIVE LOGITS
    OGND
    0.56
    AsUp
    0.52
     \%$
    0.52
     CreateTagHelper
    0.51
    %</
    0.49
     percent
    0.48
     \%)$
    0.45
    %",
    0.45
    %',
    0.45
    percent
    0.44
    Act Density 0.170%

    No Known Activations