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

    Neuronpedia

    INDEX
    Explanations

    more about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    1.18
     minimizes
    1.10
     ficou
    1.10
     అన్ని
    1.10
     maximizes
    1.09
     knows
    1.06
    reg
    1.05
    З
    1.01
     Д
    1.00
     praticamente
    1.00
    POSITIVE LOGITS
     staffers
    1.07
    mals
    1.06
    goers
    1.05
    erdings
    1.04
    其
    1.04
    ารย์
    1.02
    你
    1.02
    iritual
    1.01
    甚至
    1.00
    ⎢
    0.99
    Act Density 1.702%

    No Known Activations