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

    Neuronpedia

    INDEX
    Explanations

    seating areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.78
    k
    0.73
    ক
    0.71
    CE
    0.64
    SI
    0.61
    ก
    0.61
    ulation
    0.60
    स
    0.60
     I
    0.58
    DES
    0.58
    POSITIVE LOGITS
     seating
    0.99
    ي
    0.94
    יות
    0.89
    i
    0.86
     boissons
    0.82
    ле
    0.81
    ে
    0.81
     contrived
    0.79
    iş
    0.78
     தெரிவித்தனர்
    0.78
    Act Density 0.002%

    No Known Activations