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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =root
    -0.07
    奧
    -0.06
     xử
    -0.06
     вну
    -0.06
    .helper
    -0.06
     ncols
    -0.06
    intros
    -0.06
    Devices
    -0.06
     всем
    -0.06
     apt
    -0.06
    POSITIVE LOGITS
    licate
    0.08
    FindBy
    0.07
     が
    0.07
     Amend
    0.06
     파일
    0.06
    ậc
    0.06
    House
    0.06
    _DEFINED
    0.06
     اجرای
    0.06
     {@
    0.06
    Act Density 0.000%

    No Known Activations