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

    Neuronpedia

    INDEX
    Explanations

    Italian food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dominance
    -0.08
     lej
    -0.08
    �
    -0.08
     Raceway
    -0.08
     kjøpe
    -0.08
     arba
    -0.07
     الأسمنت
    -0.07
     appelle
    -0.07
     Acheter
    -0.07
     tegel
    -0.07
    POSITIVE LOGITS
    fold
    0.08
    Saint
    0.08
    (fun
    0.08
    inon
    0.07
    Oscar
    0.07
     flavorful
    0.07
     пом
    0.07
     contamos
    0.07
     ~(
    0.07
     Rebels
    0.07
    Act Density 0.001%

    No Known Activations