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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memory
    -0.07
     Memory
    -0.07
    >G
    -0.07
     water
    -0.06
     badge
    -0.06
     today
    -0.06
    UGINS
    -0.06
     Julian
    -0.06
    Mas
    -0.06
     talked
    -0.06
    POSITIVE LOGITS
    mada
    0.07
    事業
    0.06
    single
    0.06
    \xe
    0.06
    .twig
    0.06
    ewhere
    0.06
    seealso
    0.06
    づ
    0.06
     scrollTop
    0.06
     lineWidth
    0.06
    Act Density 0.000%

    No Known Activations