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

    Neuronpedia

    INDEX
    Explanations

    user agent

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by floating‐point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ypad
    -0.07
    AAD
    -0.07
    uktur
    -0.07
    nick
    -0.07
     esteemed
    -0.07
    jun
    -0.07
    <textarea
    -0.07
    nof
    -0.07
     řízení
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    _mu
    0.06
     slogans
    0.06
     tool
    0.06
    '{
    0.06
    -gl
    0.06
     township
    0.06
     simulations
    0.06
    .insert
    0.06
     transcription
    0.06
    .eclipse
    0.06
    Act Density 0.005%

    No Known Activations