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

    Neuronpedia

    INDEX
    Explanations

    arme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     was
    -0.06
    Would
    -0.06
     gören
    -0.06
    Was
    -0.06
     took
    -0.06
    Nevertheless
    -0.06
    <Result
    -0.06
     Already
    -0.06
    ocus
    -0.06
     discern
    -0.06
    POSITIVE LOGITS
    -mort
    0.08
    γε
    0.07
    mort
    0.07
    agi
    0.07
    सल
    0.07
    леч
    0.07
     ~/
    0.07
    орт
    0.07
    .Slf
    0.07
    arme
    0.06
    Act Density 0.014%

    No Known Activations