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

    Neuronpedia

    INDEX
    Explanations

    website names

    np_max-act · gemini-2.0-flash

    The neuron broadly detects common English words (especially high‐frequency function/content words).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     위해서
    -0.07
    ereco
    -0.06
    lcd
    -0.06
    zero
    -0.06
     mettre
    -0.06
    engl
    -0.06
    .radius
    -0.06
    ená
    -0.06
    ETHER
    -0.05
     restaurants
    -0.05
    POSITIVE LOGITS
    _external
    0.07
    _required
    0.07
    .getItemId
    0.06
    entionPolicy
    0.06
     contextual
    0.06
     retali
    0.06
    \Test
    0.06
    $_
    0.06
    _digit
    0.06
    vation
    0.06
    Act Density 0.046%

    No Known Activations