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

    Neuronpedia

    INDEX
    Explanations

    names of people or countries

    oai_token-act-pair · gemini-2.0-flash

    words with non-Latin characters or special patterns

    np_token-act-pair-logits · gpt-4o-mini

    Bali

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cataloging
    -0.58
     initComponents
    -0.54
    rawDesc
    -0.53
    httphttps
    -0.52
    AnimationFrame
    -0.51
    BeginContext
    -0.51
     tubeless
    -0.50
     ویکی‌پدیای
    -0.50
    InstrumentedTest
    -0.50
    !*\
    -0.49
    POSITIVE LOGITS
    انون
    0.52
    achim
    0.49
    uio
    0.47
     chi
    0.47
    gården
    0.46
    tuce
    0.46
    DebuggerNonUser
    0.46
     χα
    0.46
     foot
    0.46
    %)$
    0.46
    Act Density 0.480%

    No Known Activations