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

    Neuronpedia

    INDEX
    Explanations

    correctness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SET
    -0.08
    .tree
    -0.08
    就
    -0.07
    hardware
    -0.07
     butter
    -0.07
    -layer
    -0.07
     captivity
    -0.06
     measurement
    -0.06
    intree
    -0.06
    lien
    -0.06
    POSITIVE LOGITS
    ační
    0.06
    .equ
    0.06
     Vs
    0.06
     Bitcoins
    0.06
    -append
    0.06
     Democr
    0.06
     selective
    0.06
    TextEdit
    0.06
    detail
    0.06
     VOID
    0.06
    Act Density 0.005%

    No Known Activations