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

    Neuronpedia

    INDEX
    Explanations

    code and location information

    np_max-act · gemini-2.0-flash

    The neuron detects references to “candidate location” statements (including the numbered location identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    AND
    -0.06
     TORT
    -0.06
    _margin
    -0.06
     Fauc
    -0.06
    (PATH
    -0.06
    .dispatch
    -0.06
     CHO
    -0.06
     MOST
    -0.06
     Bien
    -0.06
     kiểm
    -0.06
    POSITIVE LOGITS
     gn
    0.07
    (language
    0.07
    _playlist
    0.07
     нали
    0.06
    лик
    0.06
    ga
    0.06
     thời
    0.06
     sectional
    0.06
    жі
    0.06
    キャ
    0.06
    Act Density 0.001%

    No Known Activations