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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irrational
    -0.07
     万円
    -0.06
    干
    -0.06
    λη
    -0.06
    ее
    -0.06
    udades
    -0.06
    лерг
    -0.06
    我们
    -0.06
    eres
    -0.06
    кий
    -0.06
    POSITIVE LOGITS
    stoup
    0.07
     Wichita
    0.07
     χαρα
    0.06
     müş
    0.06
     Tunisia
    0.06
     resultCode
    0.06
     Providence
    0.06
     bron
    0.06
     Humb
    0.06
     Prefer
    0.06
    Act Density 0.016%

    No Known Activations