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

    Neuronpedia

    INDEX
    Explanations

    Importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     એવા
    -0.08
     такі
    -0.08
     ongoing
    -0.08
     teil
    -0.07
    採
    -0.07
     possibilidade
    -0.07
     מדובר
    -0.07
     variant
    -0.07
     context
    -0.07
     mulighed
    -0.07
    POSITIVE LOGITS
     worthless
    0.10
     아무
    0.09
     nichts
    0.09
     niets
    0.09
     perfectly
    0.09
     ništa
    0.09
     pamusoro
    0.09
     pointless
    0.08
    Nothing
    0.08
     meaningless
    0.08
    Act Density 0.127%

    No Known Activations