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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shar
    -0.07
    固定资产
    -0.07
     giov
    -0.07
     Tanks
    -0.07
    .write
    -0.07
    ul
    -0.07
    \Type
    -0.07
     Sunrise
    -0.07
     Txt
    -0.07
     Volvo
    -0.07
    POSITIVE LOGITS
    DataService
    0.07
    阀门
    0.07
    排斥
    0.07
    .palette
    0.07
    _/
    0.06
    时常
    0.06
    _classes
    0.06
    @click
    0.06
    录取
    0.06
    伦理
    0.06
    Act Density 0.002%

    No Known Activations