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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and important events

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

    historical figures and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.45
    permitAll
    -0.34
    ConfigureAwait
    -0.31
    الدراسه
    -0.31
     muka
    -0.30
     Mau
    -0.30
     AssemblyCompany
    -0.30
    रीद
    -0.30
     anglès
    -0.29
     retrou
    -0.29
    POSITIVE LOGITS
    ########.
    0.67
     surla
    0.62
    berdayakan
    0.58
    ophanes
    0.56
    imedes
    0.54
     endregion
    0.54
     متعلقه
    0.53
    thenes
    0.52
    naeus
    0.49
    пиона
    0.48
    Act Density 0.038%

    No Known Activations