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

    Neuronpedia

    INDEX
    Explanations

    MT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hybrid
    -0.07
     Yu
    -0.06
    gow
    -0.06
     Shack
    -0.06
    eper
    -0.06
    gün
    -0.06
     Hybrid
    -0.06
     makeover
    -0.06
     Bast
    -0.06
    Modal
    -0.06
    POSITIVE LOGITS
    >%
    0.07
    □□
    0.07
     "__
    0.06
    ^
    0.06
    tracts
    0.06
     (^
    0.06
    ANJI
    0.06
    .Mongo
    0.06
    unc
    0.06
     [...]↵↵
    0.06
    Act Density 0.000%

    No Known Activations