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

    Neuronpedia

    INDEX
    Explanations

    update

    np_max-act · gemini-2.0-flash

    The neuron detects metadata markers—especially “UPDATE” tags, timestamps, and similar update/time‐stamp notations in news text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Colts
    -0.07
     rotterdam
    -0.07
    iphers
    -0.06
     enhancement
    -0.06
    	end
    -0.06
    ิงห
    -0.06
     liebe
    -0.06
    uki
    -0.06
     Estonia
    -0.06
    <A
    -0.06
    POSITIVE LOGITS
    んでいる
    0.07
    带
    0.07
     взгляд
    0.06
     INCIDENT
    0.06
    .getInput
    0.06
     время
    0.06
    Talking
    0.06
     TIMESTAMP
    0.06
    assertFalse
    0.06
    findFirst
    0.06
    Act Density 0.019%

    No Known Activations