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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     захисту
    -0.08
    sam
    -0.07
    [p
    -0.06
     Bhar
    -0.06
     usable
    -0.06
     mantener
    -0.06
     длин
    -0.06
    360
    -0.06
     quý
    -0.06
     tisí
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .json
    0.07
     DateFormat
    0.06
    <usize
    0.06
     ngại
    0.06
    .py
    0.06
     atlas
    0.06
    \Type
    0.06
    velte
    0.06
     theoretically
    0.06
    Act Density 0.016%

    No Known Activations