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

    Neuronpedia

    INDEX
    Explanations

    phen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    振动
    -0.07
     spring
    -0.07
    专注
    -0.07
     дол
    -0.07
    正值
    -0.07
     гос
    -0.06
     vacancy
    -0.06
    借
    -0.06
     heating
    -0.06
    伪造
    -0.06
    POSITIVE LOGITS
    文体
    0.07
    式
    0.07
    _Config
    0.07
     Kale
    0.07
    ออนไล
    0.07
     tostring
    0.07
     Choices
    0.07
     cref
    0.07
     diferentes
    0.06
    才发现
    0.06
    Act Density 0.012%

    No Known Activations