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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vulgar
    -0.08
     gatherings
    -0.08
     excuses
    -0.08
     attitudes
    -0.07
     divisions
    -0.07
     exaggerated
    -0.07
     ex
    -0.07
     arrogance
    -0.07
     resource
    -0.07
    ाट
    -0.07
    POSITIVE LOGITS
    씩
    0.11
    （三
    0.09
    πων
    0.08
     pangunahing
    0.08
    性质
    0.08
    线路
    0.08
     സർക്ക
    0.08
     плане
    0.08
     pathways
    0.08
     voire
    0.08
    Act Density 0.011%

    No Known Activations