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

    Neuronpedia

    INDEX
    Explanations

    events or periodic occurrences

    np_max-act · gemini-2.0-flash

    This neuron primarily detects proper names or capitalized named entities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gerekmektedir
    -0.07
     Witch
    -0.06
    hits
    -0.06
    (config
    -0.06
    gew
    -0.06
    average
    -0.06
     Craft
    -0.06
     fees
    -0.06
    inke
    -0.06
     count
    -0.06
    POSITIVE LOGITS
     açık
    0.07
     زندگی
    0.06
    ophy
    0.06
     slova
    0.06
     vzdál
    0.06
    사무
    0.06
    %"><
    0.06
     suspense
    0.06
     amph
    0.06
    Snow
    0.06
    Act Density 0.201%

    No Known Activations