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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     внимание
    -0.07
    的重点
    -0.07
    .checked
    -0.07
    iena
    -0.07
    ẫn
    -0.06
     appropriate
    -0.06
    رص
    -0.06
    ił
    -0.06
    тен
    -0.06
    力を
    -0.06
    POSITIVE LOGITS
    蚓
    0.08
     Basically
    0.07
    oooo
    0.07
     wreak
    0.07
     archae
    0.07
    的关系
    0.07
    洗衣机
    0.07
     Rockets
    0.07
    سقو
    0.07
     trademarks
    0.07
    Act Density 0.002%

    No Known Activations