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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     goodness
    -0.07
     Defaults
    -0.07
     remains
    -0.07
    .getTitle
    -0.06
    95
    -0.06
     toy
    -0.06
    bus
    -0.06
    Resource
    -0.06
    ial
    -0.06
    EMY
    -0.06
    POSITIVE LOGITS
    bild
    0.08
     okamž
    0.07
     ihn
    0.06
     rav
    0.06
     SHOP
    0.06
     AMAZ
    0.06
     RESET
    0.06
    ountries
    0.06
    (comb
    0.06
     Zah
    0.06
    Act Density 0.043%

    No Known Activations