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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jen
    -0.08
     Pare
    -0.07
     Short
    -0.07
    (ml
    -0.07
     got
    -0.07
    Dani
    -0.06
    เว
    -0.06
    不平衡
    -0.06
    栉
    -0.06
    縱
    -0.06
    POSITIVE LOGITS
     capitalists
    0.08
     viability
    0.08
     fluids
    0.08
     quantitative
    0.07
    innen
    0.07
     disciplines
    0.07
    getState
    0.07
    文学
    0.07
    打动
    0.07
     commodities
    0.07
    Act Density 0.007%

    No Known Activations