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

    Neuronpedia

    INDEX
    Explanations

    math notation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $
    1.33
    )$
    1.27
    $"
    1.23
    }$
    1.15
     }$
    1.09
     $
    1.09
     )$
    1.07
    ]$
    1.04
    )"
    1.03
    ])$
    1.03
    POSITIVE LOGITS
     utilizing
    0.80
    }}=$
    0.74
    وڈ
    0.73
     salad
    0.73
     Bonnie
    0.72
     Horde
    0.71
     AND
    0.70
     pans
    0.70
     avendo
    0.68
     ഉപയോഗ
    0.68
    Act Density 0.103%

    No Known Activations