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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בספר
    -0.07
    疫情
    -0.06
    DIC
    -0.06
    <Integer
    -0.06
    おそらく
    -0.06
    /videos
    -0.06
    Virtual
    -0.06
    Pre
    -0.06
     đệ
    -0.06
    July
    -0.06
    POSITIVE LOGITS
    下滑
    0.07
     gameTime
    0.07
    .writer
    0.07
     ensl
    0.06
    _market
    0.06
    价值
    0.06
     kisses
    0.06
     safe
    0.06
    кат
    0.06
     Shooter
    0.06
    Act Density 0.054%

    No Known Activations