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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    invoke
    -0.06
    zin
    -0.06
    ])
↵
    -0.06
     feedback
    -0.06
     Await
    -0.06
     zombies
    -0.06
     GREEN
    -0.06
    ivable
    -0.06
    _xx
    -0.05
    Danger
    -0.05
    POSITIVE LOGITS
     ByteArray
    0.08
     případě
    0.07
     schizophrenia
    0.06
     пой
    0.06
     Alexandre
    0.06
     Maze
    0.06
    common
    0.06
     Thương
    0.06
     Loader
    0.06
    BOARD
    0.06
    Act Density 0.083%

    No Known Activations