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

    Neuronpedia

    INDEX
    Explanations

    Loader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tabPage
    -0.07
     Dagger
    -0.07
    (`${
    -0.06
    bench
    -0.06
    ociety
    -0.06
    .Args
    -0.06
     facilitated
    -0.06
    dojo
    -0.06
    .Contracts
    -0.06
     Kaiser
    -0.06
    POSITIVE LOGITS
     dehydration
    0.07
    ını
    0.07
    ाम
    0.06
    ubl
    0.06
    isodes
    0.06
    enin
    0.06
    怀
    0.06
    ecause
    0.06
    DNS
    0.06
    ोख
    0.06
    Act Density 0.002%

    No Known Activations