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

    Neuronpedia

    INDEX
    Explanations

    for protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    പ
    0.39
    အတူ
    0.38
    ின்
    0.38
    ۸
    0.37
    なら
    0.37
    htaking
    0.37
    сна
    0.36
     journalist
    0.36
    퀼
    0.36
    कल्प
    0.36
    POSITIVE LOGITS
     Lament
    0.50
    LastGen
    0.49
     Prey
    0.49
     Sample
    0.48
     учу
    0.46
     मादा
    0.46
     অবধি
    0.46
     maupun
    0.45
    гии
    0.45
     proteg
    0.45
    Act Density 0.014%

    No Known Activations