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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brom
    -0.07
     irq
    -0.07
    .","
    -0.07
    관광
    -0.07
     Vulner
    -0.07
     Slovenia
    -0.07
    עצמאי
    -0.06
    .mainloop
    -0.06
     сай
    -0.06
    Streamer
    -0.06
    POSITIVE LOGITS
    𝘀
    0.07
    定位
    0.06
    則
    0.06
     vos
    0.06
     [,
    0.06
     Mission
    0.06
    𝙩
    0.06
    ،
    0.06
    ﺓ
    0.06
    APPLE
    0.06
    Act Density 0.017%

    No Known Activations