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

    Neuronpedia

    INDEX
    Explanations

    you first start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Always
    1.18
    always
    1.10
     seguirá
    1.07
     luôn
    1.06
     завжди
    1.04
    Will
    1.02
     Always
    1.02
     always
    1.01
    则
    1.00
    will
    0.99
    POSITIVE LOGITS
     inevitably
    1.21
     first
    1.21
     least
    1.19
     впервые
    1.13
     पहली
    1.12
     reaches
    1.09
     encounter
    1.08
     finally
    1.03
    初めて
    1.02
     først
    1.02
    Act Density 0.124%

    No Known Activations