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

    Neuronpedia

    INDEX
    Explanations

    code and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sacks
    1.02
     deserts
    1.00
     sacs
    1.00
     sack
    0.99
    entropy
    0.98
     grain
    0.95
     actuality
    0.95
     entropy
    0.95
    ength
    0.95
     grooms
    0.95
    POSITIVE LOGITS
     vuelve
    1.01
     nè
    0.98
    واكب
    0.98
     cần
    0.97
    ની
    0.97
     ]:
    0.96
     triển
    0.95
     कैशबैक
    0.95
     toàn
    0.95
     jedno
    0.94
    Act Density 0.175%

    No Known Activations