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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     интер
    -0.07
    👼
    -0.07
     zer
    -0.07
    🍃
    -0.07
    _verify
    -0.07
    嘴唇
    -0.07
     dışında
    -0.07
     getVersion
    -0.07
     silver
    -0.07
    ㊟
    -0.07
    POSITIVE LOGITS
     CFO
    0.07
    amines
    0.07
     unleash
    0.07
    生活方式
    0.07
    氣
    0.07
    clk
    0.06
     higher
    0.06
     Dynamic
    0.06
     поля
    0.06
    stalk
    0.06
    Act Density 0.014%

    No Known Activations