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

    Neuronpedia

    INDEX
    Explanations

    How

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NAMES
    -0.07
     Drops
    -0.07
     oxidation
    -0.07
     swelling
    -0.06
     spouses
    -0.06
    -three
    -0.06
     )[
    -0.06
     lengthy
    -0.06
     Hey
    -0.06
    JS
    -0.06
    POSITIVE LOGITS
    _singular
    0.06
    (products
    0.06
    etSocketAddress
    0.06
    engage
    0.06
    teş
    0.06
     ошиб
    0.06
     numerator
    0.06
    (enc
    0.06
    umm
    0.06
    [ii
    0.06
    Act Density 0.014%

    No Known Activations