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

    Neuronpedia

    INDEX
    Explanations

    review cons *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auto
    0.47
     enhance
    0.42
     utilise
    0.40
     fiduciary
    0.39
     versatility
    0.39
     aqu
    0.38
     versatile
    0.38
    ек
    0.38
     marc
    0.38
     pull
    0.38
    POSITIVE LOGITS
     ήταν
    0.46
    mények
    0.43
     były
    0.43
     ხელისუფ
    0.43
     była
    0.41
     だっ
    0.41
     hadde
    0.41
     있었
    0.41
    ǃ
    0.41
    ிருந்த
    0.40
    Act Density 0.000%

    No Known Activations