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

    Neuronpedia

    INDEX
    Explanations

    phrase

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     este
    0.46
     aquest
    0.45
    ນີ້
    0.44
     dette
    0.43
     aquesta
    0.43
     esse
    0.42
     this
    0.42
    了这个
    0.42
    この
    0.42
    Sixth
    0.42
    POSITIVE LOGITS
    defining
    0.38
    Rew
    0.37
     making
    0.36
     مطلوب
    0.36
     mar
    0.34
     weaken
    0.34
     law
    0.34
     weakened
    0.34
     congress
    0.33
     carta
    0.33
    Act Density 0.005%

    No Known Activations