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

    Neuronpedia

    INDEX
    Explanations

    George Zimmerman

    np_max-act · gemini-2.0-flash

    The neuron reliably fires on named entities—proper names of people (e.g. “Zimmerman,” “Trayvon”) or technical drug names (e.g. “ribavirin”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dropped
    -0.07
    .fi
    -0.06
    oq
    -0.06
     اج
    -0.06
    ufreq
    -0.06
    lat
    -0.06
     DG
    -0.06
     Fuj
    -0.06
     viewBox
    -0.06
    #+
    -0.06
    POSITIVE LOGITS
    sequence
    0.07
     Consequently
    0.07
    уванні
    0.07
     commercially
    0.07
    Everybody
    0.07
    occupation
    0.07
    conut
    0.06
     undermin
    0.06
    astically
    0.06
     elevate
    0.06
    Act Density 0.000%

    No Known Activations