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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trimmed
    -0.07
     PST
    -0.06
     XS
    -0.06
     EXPRESS
    -0.06
     Nir
    -0.06
     errs
    -0.06
     trillion
    -0.06
     vw
    -0.06
     evt
    -0.06
     thoải
    -0.06
    POSITIVE LOGITS
    ans
    0.07
     закон
    0.06
    iaomi
    0.06
     sporting
    0.06
    287
    0.06
    рас
    0.06
    /use
    0.06
     LinearLayout
    0.06
    reece
    0.06
    lua
    0.06
    Act Density 0.000%

    No Known Activations