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

    Neuronpedia

    INDEX
    Explanations

    lazy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    俵
    -0.07
    深处
    -0.07
     Duo
    -0.07
     prepare
    -0.07
     Rencontre
    -0.07
    -driver
    -0.07
     środk
    -0.07
     detr
    -0.06
    Professor
    -0.06
    不仅能
    -0.06
    POSITIVE LOGITS
     readOnly
    0.07
    LastName
    0.07
    yscale
    0.07
    ificados
    0.07
     LocalDate
    0.07
    linux
    0.07
    яз
    0.07
    	My
    0.07
    كتابة
    0.07
     hashing
    0.07
    Act Density 0.006%

    No Known Activations