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

    Neuronpedia

    INDEX
    Explanations

    Dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     उद्घ
    -0.08
     fecha
    -0.08
     प्रदर्शन
    -0.08
     தேதி
    -0.08
     उत्स
    -0.08
    日期
    -0.07
     hostess
    -0.07
     tetr
    -0.07
     तारी
    -0.07
    Fecha
    -0.07
    POSITIVE LOGITS
     비용
    0.16
     ખર્ચ
    0.15
    成本
    0.15
     costos
    0.14
     costs
    0.14
     Costs
    0.14
    Costs
    0.14
     هزینه
    0.14
     prices
    0.14
     custos
    0.14
    Act Density 0.028%

    No Known Activations