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
    kul
    -0.07
     dataframe
    -0.07
    增长
    -0.07
    Thu
    -0.06
    4
    -0.06
     año
    -0.06
    율
    -0.06
    Ash
    -0.06
    tell
    -0.06
     year
    -0.06
    POSITIVE LOGITS
    .matmul
    0.06
     Odd
    0.06
    .initState
    0.06
    暗
    0.06
     bake
    0.06
     contacted
    0.06
     romance
    0.06
     ovarian
    0.06
    puted
    0.06
    sembler
    0.06
    Act Density 0.080%

    No Known Activations