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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RADIUS
    -0.06
     Bang
    -0.06
    .Power
    -0.06
     н
    -0.06
    .CheckedChanged
    -0.06
     months
    -0.06
     featuring
    -0.06
     graphql
    -0.06
    adays
    -0.06
    ispers
    -0.06
    POSITIVE LOGITS
    không
    0.07
     بین
    0.06
    ";
↵
    0.06
    ("="
    0.06
     hele
    0.06
    Album
    0.06
     và
    0.06
     batching
    0.06
    478
    0.06
     cyclist
    0.06
    Act Density 0.085%

    No Known Activations