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

    Neuronpedia

    INDEX
    Explanations

    End of sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     свойства
    -0.07
    Workflow
    -0.06
    сутств
    -0.06
    維
    -0.06
     improper
    -0.06
    یمی
    -0.06
    ='')↵
    -0.06
    .Return
    -0.05
     المم
    -0.05
    >false
    -0.05
    POSITIVE LOGITS
     Amendments
    0.08
    医
    0.07
    詩
    0.06
     lv
    0.06
    (rate
    0.06
    ่าวว
    0.06
     Brah
    0.06
     Sund
    0.06
     plais
    0.06
     دول
    0.06
    Act Density 0.000%

    No Known Activations