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

    Neuronpedia

    INDEX
    Explanations

    large numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bbene
    -0.82
     vérit
    -0.80
     jouets
    -0.79
     générations
    -0.79
     varandra
    -0.79
     mères
    -0.78
     oreilles
    -0.77
     engraçadas
    -0.77
     témoins
    -0.74
     leçons
    -0.74
    POSITIVE LOGITS
     dollars
    0.66
    ally
    0.57
     six
    0.55
    PerformLayout
    0.54
     four
    0.54
     nine
    0.54
     dollar
    0.53
    omiya
    0.53
     sixth
    0.52
    ously
    0.52
    Act Density 0.020%

    No Known Activations