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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punching
    -0.06
    -around
    -0.06
    	Me
    -0.06
     GameState
    -0.06
     distributing
    -0.06
    ONE
    -0.06
    н
    -0.06
    Inputs
    -0.06
    ea
    -0.06
    stacles
    -0.06
    POSITIVE LOGITS
     compuls
    0.08
     unre
    0.07
    [sub
    0.06
     замов
    0.06
     σει
    0.06
     **
    0.06
     Fired
    0.06
    หล
    0.06
     आय
    0.06
     wished
    0.06
    Act Density 0.008%

    No Known Activations