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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     себя
    -0.08
    mint
    -0.07
     buckets
    -0.07
    ӣ
    -0.07
    働
    -0.07
     clause
    -0.06
    觉得
    -0.06
     decade
    -0.06
    .active
    -0.06
    |(
    -0.06
    POSITIVE LOGITS
    电阻
    0.07
     criança
    0.07
     relação
    0.07
     essential
    0.07
     рек
    0.07
     lenght
    0.07
    ático
    0.06
     représent
    0.06
     nächsten
    0.06
     hệ
    0.06
    Act Density 0.000%

    No Known Activations