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

    Neuronpedia

    INDEX
    Explanations

    Repeaters/repeating devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hood
    -0.08
    .billing
    -0.08
     mailing
    -0.08
     Bowling
    -0.08
     bowling
    -0.08
    cox
    -0.08
    暴
    -0.07
     vincul
    -0.07
    jury
    -0.07
     tapestry
    -0.07
    POSITIVE LOGITS
     boosts
    0.10
     repe
    0.09
     ആവ
    0.09
     boosting
    0.09
     промеж
    0.09
     қажет
    0.08
     repetir
    0.08
    重复
    0.08
    节点
    0.08
     Zwischen
    0.08
    Act Density 0.003%

    No Known Activations