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

    Neuronpedia

    INDEX
    Explanations

    lists of numbers

    np_max-act · gemini-2.0-flash

    The primary thing this neuron does is detect numeric tokens (digits and numeric expressions) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     openid
    -0.07
    .getContext
    -0.06
    >alert
    -0.06
    	y
    -0.06
    πουργ
    -0.06
    .install
    -0.06
    icích
    -0.06
     Ruf
    -0.06
    /angular
    -0.06
    irth
    -0.06
    POSITIVE LOGITS
    PRO
    0.07
    pro
    0.07
     Descriptor
    0.06
    ريق
    0.06
    ním
    0.06
     priv
    0.06
    iev
    0.06
    AtA
    0.06
     gra
    0.06
    Dot
    0.06
    Act Density 0.023%

    No Known Activations