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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .records
    -0.07
     confessed
    -0.07
    	Double
    -0.06
    	    ↵
    -0.06
    gem
    -0.06
    	DB
    -0.06
     Siege
    -0.06
     Mart
    -0.06
     rode
    -0.06
    悲
    -0.06
    POSITIVE LOGITS
    ANDOM
    0.08
    ',↵↵
    0.06
    ạy
    0.06
    >(&
    0.06
    ंख
    0.06
    ::$
    0.06
    )((((
    0.06
     العظ
    0.06
     condu
    0.06
    ysl
    0.06
    Act Density 0.645%

    No Known Activations