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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loc
    -0.07
    杜
    -0.06
    ¨ط
    -0.06
    eva
    -0.06
     部
    -0.06
    杨
    -0.06
     endwhile
    -0.06
     riot
    -0.06
    ]);
↵
    -0.06
     Graz
    -0.06
    POSITIVE LOGITS
     gestion
    0.08
    新
    0.07
    ventory
    0.07
    finding
    0.07
     manages
    0.06
    éry
    0.06
    .mozilla
    0.06
     κορ
    0.06
     chemotherapy
    0.06
     Specifically
    0.06
    Act Density 0.027%

    No Known Activations