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

    Neuronpedia

    INDEX
    Explanations

    location names

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the administrative‐division term “Department” (especially in “Department of …” or “Departments of …” contexts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (schedule
    -0.07
    _sim
    -0.06
    Mu
    -0.06
     arousal
    -0.06
     mix
    -0.06
     Flat
    -0.06
    aria
    -0.06
     AXIS
    -0.06
     references
    -0.06
     HOT
    -0.06
    POSITIVE LOGITS
    اعية
    0.07
    etine
    0.07
    tarı
    0.07
     تحت
    0.07
     στις
    0.06
     Routes
    0.06
     ctx
    0.06
    }px
    0.06
    _codes
    0.06
     сопров
    0.06
    Act Density 0.007%

    No Known Activations