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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;left
    -0.07
    皇
    -0.06
    (||
    -0.06
    <<"
    -0.06
     Tantra
    -0.06
     antioxidants
    -0.06
    xEE
    -0.06
     obj
    -0.06
     };
↵
    -0.06
     ưu
    -0.06
    POSITIVE LOGITS
    sdale
    0.09
    bak
    0.08
    ड
    0.08
     handset
    0.08
     �
    0.07
    符
    0.07
    須
    0.07
    885
    0.07
    ことも
    0.07
     Sizes
    0.07
    Act Density 0.025%

    No Known Activations