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

    Neuronpedia

    INDEX
    Explanations

    breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    0.84
     [
    0.81
     Also
    0.80
     so
    0.77
     ]
    0.76
     desire
    0.74
     an
    0.74
     توجه
    0.73
     would
    0.71
     (
    0.71
    POSITIVE LOGITS
    товые
    1.19
    ®,
    1.15
    тивные
    1.09
    ные
    1.04
    товых
    1.02
    өт
    1.00
    opoly
    1.00
    opathies
    0.99
     និង
    0.99
    ческие
    0.99
    Act Density 1.016%

    No Known Activations