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

    Neuronpedia

    INDEX
    Explanations

    sorting and discarding items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foul
    -0.09
     BY
    -0.08
    &page
    -0.07
     MAN
    -0.07
    truction
    -0.07
     применения
    -0.07
    -store
    -0.07
     Brook
    -0.07
    erialization
    -0.07
    -window
    -0.07
    POSITIVE LOGITS
     medications
    0.09
    无法
    0.08
     давно
    0.08
    ូម
    0.08
     Medikamente
    0.08
     masa
    0.08
     лекарства
    0.08
    制服
    0.08
     timeless
    0.07
    odno
    0.07
    Act Density 0.005%

    No Known Activations