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

    Neuronpedia

    INDEX
    Explanations

    betonen mit kritik

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оптима
    0.50
     Benutz
    0.46
     kullanıl
    0.44
     Benutzer
    0.43
     optimal
    0.42
     உண்ட
    0.42
     Просто
    0.42
     kullanılır
    0.42
    Optimal
    0.40
    你可以
    0.40
    POSITIVE LOGITS
     formulated
    0.59
     formulate
    0.59
     крити
    0.58
     konkret
    0.57
     kritik
    0.55
     iron
    0.54
     krit
    0.54
     konkre
    0.53
     ironically
    0.52
     сфор
    0.52
    Act Density 0.009%

    No Known Activations