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

    Neuronpedia

    INDEX
    Explanations

    code exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (encoding
    -0.06
     спроб
    -0.06
     walkers
    -0.06
    uesta
    -0.06
    irror
    -0.06
     iddi
    -0.06
     tecr
    -0.06
     Benef
    -0.06
     산업
    -0.06
    हन
    -0.06
    POSITIVE LOGITS
     scaler
    0.08
    153
    0.07
    -big
    0.06
    571
    0.06
     Shank
    0.06
     Common
    0.06
    Subjects
    0.06
    893
    0.06
     Leah
    0.06
     Kensington
    0.06
    Act Density 0.000%

    No Known Activations