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

    Neuronpedia

    INDEX
    Explanations

    awards and honors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வற்றை
    0.38
    尔
    0.38
     progressivement
    0.36
     отчет
    0.30
    arashtra
    0.30
     व्यापक
    0.29
     صارفین
    0.29
    增大
    0.29
    et
    0.28
    ็ก
    0.28
    POSITIVE LOGITS
     awarded
    0.36
     recipient
    0.34
     nominee
    0.32
     !
    0.31
     medal
    0.31
     headphone
    0.31
     winner
    0.31
     നേടിയ
    0.30
     in
    0.30
     twice
    0.29
    Act Density 0.030%

    No Known Activations