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

    Neuronpedia

    INDEX
    Explanations

    adapting something for use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuts
    -0.06
     oppon
    -0.06
    .Cloud
    -0.06
     representations
    -0.06
     Timeout
    -0.06
     besteht
    -0.06
    stairs
    -0.06
    Nested
    -0.06
    WD
    -0.06
     становить
    -0.06
    POSITIVE LOGITS
    .workspace
    0.07
    0.07
    δης
    0.07
    istency
    0.06
    cot
    0.06
    voř
    0.06
    isine
    0.06
    sono
    0.06
    trip
    0.06
    anguard
    0.06
    Act Density 0.025%

    No Known Activations