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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     полос
    -0.06
    ‐'
    -0.06
    ())[
    -0.06
     favorite
    -0.06
     ate
    -0.06
    agues
    -0.06
    .square
    -0.06
     increases
    -0.06
     Wolfe
    -0.06
    .Tensor
    -0.05
    POSITIVE LOGITS
    né
    0.07
    希
    0.07
    tf
    0.07
    -root
    0.07
     gigg
    0.07
    rnek
    0.06
    реб
    0.06
    $body
    0.06
    outputs
    0.06
    -schema
    0.06
    Act Density 0.000%

    No Known Activations