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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash

    descriptions of scientific methods and their implications in various studies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .helpers
    -0.07
    STEP
    -0.07
    noteq
    -0.06
    @nate
    -0.06
    (ic
    -0.06
    就会
    -0.06
    _until
    -0.06
    .populate
    -0.06
    LAY
    -0.06
    .worker
    -0.06
    POSITIVE LOGITS
     Alf
    0.07
    0.07
     $_[
    0.07
    сед
    0.07
    amanho
    0.07
     mud
    0.07
     Settlement
    0.07
     settlements
    0.07
     Drinking
    0.06
     Lif
    0.06
    Act Density 0.032%

    No Known Activations