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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric tokens containing decimal points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ?>↵↵↵
    -0.07
     Міністер
    -0.07
    '}}>↵
    -0.07
    提示
    -0.07
    (fin
    -0.07
    DIS
    -0.07
     dall
    -0.07
     شهرد
    -0.06
    	Use
    -0.06
    '↵↵↵↵
    -0.06
    POSITIVE LOGITS
    �
    0.07
    анная
    0.06
    oeff
    0.06
    .cancel
    0.06
    ें।
    0.06
     advertisers
    0.06
    codec
    0.06
    rika
    0.06
    Audio
    0.05
     Dě
    0.05
    Act Density 0.111%

    No Known Activations