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

    Neuronpedia

    INDEX
    Explanations

    German word im/am

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pillars
    -0.08
     الإن
    -0.07
     Stoke
    -0.07
     Affiliate
    -0.07
     douche
    -0.07
    .Fetch
    -0.07
     Вот
    -0.07
    rones
    -0.07
     سبحان
    -0.07
     alguien
    -0.07
    POSITIVE LOGITS
    owego
    0.08
    tryside
    0.08
    mast
    0.07
    第三
    0.07
    (Controller
    0.07
    ữ
    0.07
    uyo
    0.07
     {...
    0.07
     bild
    0.07
    	m
    0.07
    Act Density 0.009%

    No Known Activations