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

    Neuronpedia

    INDEX
    Explanations

    ible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nal
    -0.09
     землю
    -0.08
     мера
    -0.08
     мақ
    -0.08
     зем
    -0.08
     wraz
    -0.07
    .clock
    -0.07
    Stages
    -0.07
     같
    -0.07
    orera
    -0.07
    POSITIVE LOGITS
     પ્રવ
    0.09
    ുവര
    0.09
    娱乐
    0.08
     innovatie
    0.08
    UEST
    0.08
     અસ
    0.08
     innovation
    0.08
     activity
    0.08
    娛樂
    0.07
     entertainment
    0.07
    Act Density 0.016%

    No Known Activations