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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ledged
    -0.09
     bud
    -0.07
     bulund
    -0.07
     Collect
    -0.07
     burns
    -0.06
    蔹
    -0.06
     versch
    -0.06
     jap
    -0.06
     כת
    -0.06
    حلول
    -0.06
    POSITIVE LOGITS
     ',↵
    0.08
    .AF
    0.07
    onn
    0.07
     #
↵
    0.07
    >-->↵
    0.07
    PLATFORM
    0.07
    板
    0.07
     pai
    0.07
     что
    0.07
     #↵
    0.07
    Act Density 0.001%

    No Known Activations