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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on the French word “confiné.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .HashSet
    -0.06
    finite
    -0.06
    LU
    -0.06
     technological
    -0.06
    theros
    -0.06
    換
    -0.06
    %";↵
    -0.06
    positor
    -0.06
    places
    -0.06
    誤
    -0.06
    POSITIVE LOGITS
     zel
    0.07
    (program
    0.06
    urm
    0.06
     dưỡng
    0.06
     зел
    0.06
    ₁
    0.06
     Cook
    0.06
    .Guid
    0.06
     živ
    0.06
     přibliž
    0.06
    Act Density 0.004%

    No Known Activations