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

    Neuronpedia

    INDEX
    Explanations

    to be verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    描
    -0.07
     scaling
    -0.07
     동일
    -0.06
    	Default
    -0.06
     portrayed
    -0.06
     preaching
    -0.06
    Metadata
    -0.06
     hustle
    -0.06
     invoking
    -0.06
     fencing
    -0.06
    POSITIVE LOGITS
    ########################################################
    0.07
    /car
    0.06
     Raqqa
    0.06
     chóng
    0.06
    yar
    0.06
     �
    0.06
    Ошибка
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
     kapsamında
    0.06
    (Dense
    0.06
    Act Density 0.059%

    No Known Activations