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

    Neuronpedia

    INDEX
    Explanations

    math variable assignments

    np_max-act · gemini-2.0-flash

    This neuron detects decimal (floating‐point) numeric literals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cerc
    -0.06
     дав
    -0.06
    Women
    -0.06
    Redux
    -0.06
     recurs
    -0.06
     Brace
    -0.06
     اختصاص
    -0.06
    >".
    -0.06
    sockopt
    -0.06
    -threat
    -0.06
    POSITIVE LOGITS
     января
    0.08
    /student
    0.07
     ノ
    0.07
     stadiums
    0.06
    时间
    0.06
    })",
    0.06
     leží
    0.06
     settle
    0.06
     dst
    0.06
    τερ
    0.06
    Act Density 0.003%

    No Known Activations