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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enriched
    -0.08
    explo
    -0.07
     open
    -0.07
    rites
    -0.07
     تل
    -0.06
     Clean
    -0.06
    توبر
    -0.06
     Open
    -0.06
     Formal
    -0.06
     compreh
    -0.06
    POSITIVE LOGITS
    )
    0.07
    '],
↵
    0.07
    acaktır
    0.07
     rr
    0.07
    	ar
    0.06
    ())
↵
↵
    0.06
    ]]
↵
    0.06
     Fleet
    0.06
    ्छ
    0.06
    ),$
    0.06
    Act Density 0.033%

    No Known Activations