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

    Neuronpedia

    INDEX
    Explanations

    defining or explaining phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unele
    0.54
     aufgrund
    0.50
     cosa
    0.48
     Niall
    0.46
     Gunners
    0.46
     Austria
    0.46
     Dublin
    0.46
     trotz
    0.46
    androidx
    0.45
     Blanch
    0.45
    POSITIVE LOGITS
    gena
    0.42
    le
    0.40
    raj
    0.39
     작
    0.38
    ikal
    0.38
    ling
    0.38
    water
    0.37
    ok
    0.37
    Ģ
    0.37
     покры
    0.37
    Act Density 0.003%

    No Known Activations