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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and does not detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mbH
    -0.07
    (Equal
    -0.07
    quee
    -0.06
    ffen
    -0.06
    ネット
    -0.06
    consts
    -0.06
    "d
    -0.06
     یافت
    -0.06
    enario
    -0.06
     セ
    -0.06
    POSITIVE LOGITS
    'icon
    0.06
    /top
    0.06
    -development
    0.06
     चल
    0.06
    -comp
    0.06
    currentColor
    0.06
    stddef
    0.06
    ائرة
    0.06
    -init
    0.06
    .tim
    0.06
    Act Density 0.002%

    No Known Activations