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

    Neuronpedia

    INDEX
    Explanations

    adjusting accordingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nghe
    0.35
     sclerosis
    0.35
    슨
    0.35
     overseen
    0.33
    abung
    0.32
     없고
    0.32
    ྲ
    0.31
     vitro
    0.31
    '"
    0.31
    任何人
    0.31
    POSITIVE LOGITS
     accordingly
    1.74
     Accordingly
    1.46
    Accordingly
    1.37
     correspondingly
    1.26
     соответственно
    1.19
     entsprechend
    1.16
     त्यानुसार
    1.13
     appropriately
    1.12
     відповідно
    1.05
     Соответ
    1.03
    Act Density 0.019%

    No Known Activations