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

    Neuronpedia

    INDEX
    Explanations

    alternate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     western
    -0.08
     знать
    -0.08
     kindly
    -0.08
     కో
    -0.08
    лением
    -0.08
     Anne
    -0.07
     Lod
    -0.07
    ектер
    -0.07
    _ft
    -0.07
     WEST
    -0.07
    POSITIVE LOGITS
     altern
    0.08
     alternating
    0.08
     વખત
    0.08
    -अलग
    0.08
     Erfolg
    0.07
    �
    0.07
    กัน
    0.07
     liga
    0.07
     Berd
    0.07
     festen
    0.07
    Act Density 0.008%

    No Known Activations