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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卡片
    -0.08
    矬
    -0.07
     fiscal
    -0.07
    سا
    -0.07
     text
    -0.07
     Reach
    -0.07
     Increment
    -0.07
     ledge
    -0.07
    rough
    -0.07
    7
    -0.07
    POSITIVE LOGITS
     caf
    0.07
    langs
    0.07
    (my
    0.07
     Yankees
    0.07
     między
    0.07
     hiçbir
    0.07
    .mongo
    0.07
    も
    0.07
    -blocking
    0.07
    .OutputStream
    0.06
    Act Density 0.045%

    No Known Activations