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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .↵↵↵↵↵↵
    -0.07
    ीटर
    -0.07
    .green
    -0.06
    Expressions
    -0.06
     استفاده
    -0.06
    ॉप
    -0.06
    amer
    -0.06
     replacements
    -0.06
    CommandLine
    -0.06
     exceeded
    -0.06
    POSITIVE LOGITS
     SPELL
    0.07
    venues
    0.07
     Missile
    0.06
    .Series
    0.06
    .dylib
    0.06
    زش
    0.06
     gdy
    0.06
     Birch
    0.06
     Moran
    0.06
    埋
    0.06
    Act Density 0.002%

    No Known Activations