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

    Neuronpedia

    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     برای
    -0.08
     Benghazi
    -0.07
     풍
    -0.07
    ьогод
    -0.07
    -forward
    -0.07
    	tc
    -0.06
     مقد
    -0.06
     Stamina
    -0.06
    Spo
    -0.06
    ・
    -0.06
    POSITIVE LOGITS
     --------↵
    0.06
    utch
    0.06
    >All
    0.06
    Same
    0.06
    _${
    0.06
    dın
    0.06
    .Void
    0.06
     органів
    0.06
    _chars
    0.06
     некоторые
    0.06
    Act Density 0.059%

    No Known Activations