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

    Neuronpedia

    INDEX
    Explanations

    describing beautiful places and sights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    1.34
    e
    1.24
    t
    1.22
    p
    1.18
    g
    1.15
    ه
    1.13
    j
    1.05
    a
    1.02
    o
    0.85
     is
    0.85
    POSITIVE LOGITS
     заяви
    0.90
     ल
    0.88
    ра
    0.88
     созда
    0.84
    \}.
    0.83
    ine
    0.82
     था
    0.79
     maggio
    0.78
    र्गत
    0.78
     እና
    0.77
    Act Density 0.002%

    No Known Activations