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

    Neuronpedia

    INDEX
    Explanations

    parchment paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PROM
    0.98
    RENCE
    0.96
     cuba
    0.93
     exons
    0.92
    Ngày
    0.88
    Gosudarstvennyj
    0.87
    Bayern
    0.86
     Piy
    0.86
     Roundtable
    0.86
     Vũ
    0.85
    POSITIVE LOGITS
    liness
    1.27
    л
    1.24
    а
    1.20
    о
    1.14
    iving
    1.13
    то
    1.10
    tos
    1.08
    ло
    1.06
    у
    1.05
    ाय
    1.05
    Act Density 0.011%

    No Known Activations