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

    Neuronpedia

    INDEX
    Explanations

    language learning vocabulary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crates
    -0.08
    (days
    -0.08
     ನಿರ್ದೇಶ
    -0.08
    dirs
    -0.08
     acct
    -0.08
     abst
    -0.08
     dst
    -0.08
    (ac
    -0.08
    _submission
    -0.08
    	dst
    -0.08
    POSITIVE LOGITS
    ک
    0.07
    import
    0.07
     benchmarking
    0.07
    valuable
    0.07
     recurring
    0.07
    batim
    0.07
    常
    0.07
     phrase
    0.07
     dosage
    0.07
    丸
    0.07
    Act Density 0.005%

    No Known Activations