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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    óg
    -0.08
    ös
    -0.08
    ruption
    -0.07
    öğ
    -0.07
    ಗ
    -0.07
    olutely
    -0.07
    طرق
    -0.07
    طف
    -0.07
    公开招聘
    -0.07
    Stopping
    -0.07
    POSITIVE LOGITS
    ="";↵
    0.07
    ("-");↵
    0.07
     "";
    0.07
     при
    0.07
     ');↵
    0.07
    )));↵
    0.07
    浬
    0.06
    ","");↵
    0.06
    很正常
    0.06
    getContent
    0.06
    Act Density 0.011%

    No Known Activations