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

    Neuronpedia

    INDEX
    Explanations

    code parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drawable
    -0.08
    .After
    -0.07
    应邀
    -0.07
     Solve
    -0.07
    .This
    -0.07
    .He
    -0.07
    subjects
    -0.07
    💘
    -0.07
    alleries
    -0.06
    减持
    -0.06
    POSITIVE LOGITS
    Ю
    0.08
     biomedical
    0.07
     advisory
    0.06
     חופ
    0.06
    鼬
    0.06
     breaches
    0.06
     Recommendations
    0.06
    iers
    0.06
    ই
    0.06
    ём
    0.06
    Act Density 0.128%

    No Known Activations