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

    Neuronpedia

    INDEX
    Explanations

    references to popular cultural figures or characters

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

    Appears before capitalized abbreviations or names

    np_acts-logits-general · gemini-2.0-flash

    names, titles, and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.94
    TestingModule
    -0.62
    XmlAccessType
    -0.62
    énario
    -0.59
    aderie
    -0.59
    unately
    -0.59
    Referanser
    -0.59
    \{\\
    -0.58
    npos
    -0.57
     références
    -0.57
    POSITIVE LOGITS
    ◯
    0.52
    🅱
    0.50
    $-
    0.49
    dirond
    0.49
     Waray
    0.48
     Mening
    0.47
    town
    0.47
    PhysRevLett
    0.47
    ky
    0.46
    ?!”
    0.46
    Act Density 0.373%

    No Known Activations