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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *****↵
    -0.07
    摸
    -0.07
    亦
    -0.06
     ();↵↵
    -0.06
     Granny
    -0.06
    BBBB
    -0.06
    phanumeric
    -0.06
     две
    -0.06
     다시
    -0.06
    τός
    -0.06
    POSITIVE LOGITS
    ,key
    0.06
     Goku
    0.06
     openings
    0.06
     estimation
    0.06
    урс
    0.06
    Hay
    0.06
     müc
    0.06
    業
    0.06
    .tech
    0.06
     Prior
    0.06
    Act Density 0.014%

    No Known Activations