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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amient
    -0.06
     fft
    -0.06
    ificado
    -0.06
     Kashmir
    -0.06
    ванов
    -0.06
    ाश
    -0.06
     increments
    -0.05
    variant
    -0.05
    ็น
    -0.05
    更加
    -0.05
    POSITIVE LOGITS
    Shield
    0.07
    vise
    0.06
     客
    0.06
    Лю
    0.06
    เกษ
    0.06
    ayıp
    0.06
    ”),
    0.06
    .lat
    0.06
     Martha
    0.06
    Lo
    0.06
    Act Density 0.042%

    No Known Activations