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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snaps
    -0.07
    力的
    -0.06
    ''.
    -0.06
    '-
    -0.06
    go
    -0.06
    (FILE
    -0.06
    uden
    -0.06
    jan
    -0.06
    Runs
    -0.06
    .snp
    -0.06
    POSITIVE LOGITS
     ounce
    0.07
     masse
    0.07
     hinge
    0.07
     diced
    0.06
     wandering
    0.06
    �
    0.06
     ảnh
    0.06
     icons
    0.06
     pwd
    0.06
    منی
    0.06
    Act Density 0.023%

    No Known Activations