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

    Neuronpedia

    INDEX
    Explanations

    Expressing gratitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LLU
    -0.06
    Summary
    -0.06
     Banner
    -0.06
    袖
    -0.06
     lecturer
    -0.06
     replica
    -0.06
    Кон
    -0.06
     �
    -0.06
     Ritch
    -0.06
     तथ
    -0.05
    POSITIVE LOGITS
    urent
    0.07
    895
    0.07
     tespit
    0.06
     운영
    0.06
    azers
    0.06
    658
    0.06
    ução
    0.06
     человеч
    0.06
     TODO
    0.06
    .MONTH
    0.06
    Act Density 0.049%

    No Known Activations