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

    Neuronpedia

    INDEX
    Explanations

    book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    歷
    -0.07
    ίος
    -0.07
     anomaly
    -0.07
     estas
    -0.07
     네이트온
    -0.06
     نس
    -0.06
    模
    -0.06
     Arbeit
    -0.06
     �
    -0.06
     घ
    -0.06
    POSITIVE LOGITS
    async
    0.06
    	ch
    0.06
    čním
    0.06
     nil
    0.06
     accept
    0.06
    unft
    0.06
     rtc
    0.06
    >Total
    0.06
    .zero
    0.06
    tiğini
    0.06
    Act Density 0.009%

    No Known Activations