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

    Neuronpedia

    INDEX
    Explanations

    Reserve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     крит
    -0.07
     Ci
    -0.07
    ScreenWidth
    -0.07
     architectural
    -0.06
    eniz
    -0.06
    実
    -0.06
     Curt
    -0.06
     آنان
    -0.06
     Cum
    -0.06
    coeff
    -0.06
    POSITIVE LOGITS
     Reserve
    0.10
     {!!
    0.07
    ヨ
    0.06
     waste
    0.06
     BTC
    0.06
     çıkış
    0.06
     bones
    0.06
     overseeing
    0.06
    ves
    0.06
    .save
    0.06
    Act Density 0.002%

    No Known Activations