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

    Neuronpedia

    INDEX
    Explanations

    code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Match
    -0.29
     Matches
    -0.26
    ä¸»å¼ł
    -0.26
    Match
    -0.26
    _MATCH
    -0.25
    èµ°å»Ĭ
    -0.25
    Matches
    -0.25
     matches
    -0.25
     closet
    -0.24
    zilla
    -0.24
    POSITIVE LOGITS
    idency
    0.32
     release
    0.30
    软
    0.29
     Release
    0.28
     released
    0.28
    ialias
    0.28
    ynos
    0.28
    _release
    0.27
     releasing
    0.27
    Release
    0.26
    Act Density 1.392%

    No Known Activations