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

    Neuronpedia

    INDEX
    Explanations

    round

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &id
    -0.07
     jejichž
    -0.07
    ration
    -0.07
     Bên
    -0.07
     susceptibility
    -0.07
     ngay
    -0.07
     pů
    -0.06
     Split
    -0.06
     Script
    -0.06
     overwhelmed
    -0.06
    POSITIVE LOGITS
    325
    0.06
    astics
    0.06
    τουργ
    0.06
     '',
↵
    0.06
    colm
    0.06
     +
↵
    0.06
    いの
    0.06
     конферен
    0.06
    done
    0.06
    Carol
    0.06
    Act Density 0.002%

    No Known Activations