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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coin
    -0.08
     EXPECT
    -0.08
    Coin
    -0.08
     пасп
    -0.08
    贤
    -0.08
     станции
    -0.08
     MATCH
    -0.08
     прекращ
    -0.08
     reiz
    -0.07
     normals
    -0.07
    POSITIVE LOGITS
     intense
    0.08
     newfound
    0.08
    力量
    0.07
     जब
    0.07
     carn
    0.07
     imagination
    0.07
     قوة
    0.07
     내용
    0.07
     grooves
    0.07
     chứa
    0.07
    Act Density 0.011%

    No Known Activations