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

    Neuronpedia

    INDEX
    Explanations

    Software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    عان
    -0.07
     Uns
    -0.07
    탁
    -0.07
    4
    -0.06
     conditioner
    -0.06
     humans
    -0.06
     pais
    -0.06
    سطس
    -0.06
    is
    -0.06
     nói
    -0.06
    POSITIVE LOGITS
     createUser
    0.07
     Authentication
    0.07
    	connect
    0.06
     روست
    0.06
     Tales
    0.06
     fitting
    0.06
     document
    0.06
    argv
    0.06
     //}↵
    0.06
    (graph
    0.05
    Act Density 0.005%

    No Known Activations