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
     Utility
    -0.07
     animation
    -0.07
     Bangalore
    -0.07
     endeavour
    -0.06
     Animation
    -0.06
     Byte
    -0.06
     Apprentice
    -0.06
     CI
    -0.06
     reservation
    -0.06
     GA
    -0.06
    POSITIVE LOGITS
     "'.$
    0.07
    ární
    0.07
    .PictureBox
    0.07
    lbrakk
    0.07
    ческим
    0.06
     prům
    0.06
    ây
    0.06
    =$('#
    0.06
    %;">↵
    0.06
    ="--
    0.06
    Act Density 0.008%

    No Known Activations