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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -shift
    -0.07
     exhibit
    -0.06
     alan
    -0.06
    queryParams
    -0.06
     swapping
    -0.06
    	border
    -0.06
    ند
    -0.06
    enc
    -0.06
     tilted
    -0.06
     algunas
    -0.06
    POSITIVE LOGITS
    设计器
    0.08
     ):
    0.07
     اعتر
    0.07
    κτη
    0.07
    ieder
    0.07
     vzdu
    0.06
    ethnic
    0.06
     nex
    0.06
     تازه
    0.06
     люди
    0.06
    Act Density 0.030%

    No Known Activations