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

    Neuronpedia

    INDEX
    Explanations

    Programming/web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    timing
    -0.07
     Geography
    -0.07
     communism
    -0.07
    :left
    -0.07
     Books
    -0.07
     أغ
    -0.06
    、と
    -0.06
    iana
    -0.06
     antics
    -0.06
     simulation
    -0.06
    POSITIVE LOGITS
    -can
    0.07
    .Run
    0.06
    umann
    0.06
    leaning
    0.06
     evangel
    0.06
     contenders
    0.06
    -lived
    0.06
     Counseling
    0.06
     srov
    0.06
     assertTrue
    0.06
    Act Density 0.000%

    No Known Activations