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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash

    This neuron detects French location terms—especially “quartier” (and related district words) in French text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     operation
    -0.07
     classroom
    -0.07
    namespace
    -0.07
     theirs
    -0.06
     Universe
    -0.06
    _COMPLEX
    -0.06
     Pra
    -0.06
     speech
    -0.06
    |h
    -0.06
     خلال
    -0.06
    POSITIVE LOGITS
    合わせ
    0.07
    contacts
    0.07
     initData
    0.06
     빈
    0.06
    IDDEN
    0.06
    -Owned
    0.06
    deps
    0.06
    vod
    0.06
    χη
    0.06
     الشم
    0.06
    Act Density 0.284%

    No Known Activations