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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ानक
    -0.07
     twenties
    -0.07
    айд
    -0.07
    edges
    -0.07
     德
    -0.06
    ुकस
    -0.06
    tv
    -0.06
    (op
    -0.06
    _box
    -0.06
    Multiple
    -0.06
    POSITIVE LOGITS
    (protocol
    0.06
    }>{
    0.06
     jih
    0.06
    ValueCollection
    0.06
     surre
    0.06
    processors
    0.06
    	this
    0.06
     gia
    0.06
     exporters
    0.06
     welcomes
    0.06
    Act Density 0.018%

    No Known Activations