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

    Neuronpedia

    INDEX
    Explanations

    demographics

    np_max-act · gemini-2.0-flash

    The neuron primarily detects decimal-formatted numerical values (numbers with a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .*↵↵
    -0.07
    THEN
    -0.07
     THEN
    -0.06
    between
    -0.06
     closed
    -0.06
     probably
    -0.06
    ’nin
    -0.06
    렇
    -0.06
    libs
    -0.06
     svou
    -0.06
    POSITIVE LOGITS
     Georg
    0.07
    けない
    0.06
    говор
    0.06
    ुं
    0.06
     Báo
    0.06
    989
    0.06
    /down
    0.06
     Caval
    0.06
    Grupo
    0.06
     Ziel
    0.06
    Act Density 0.002%

    No Known Activations