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

    Neuronpedia

    INDEX
    Explanations

    material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Memorial
    -0.08
     Rite
    -0.08
     reminis
    -0.07
    欢
    -0.07
    কাল
    -0.07
     pruž
    -0.07
    çilik
    -0.07
    열
    -0.07
     steady
    -0.07
     festivities
    -0.07
    POSITIVE LOGITS
     суще
    0.10
     diferencias
    0.10
     impactful
    0.10
     significance
    0.09
     disagreement
    0.09
     существенно
    0.09
     disagreements
    0.09
     significativamente
    0.09
    重大
    0.09
     differences
    0.08
    Act Density 0.029%

    No Known Activations