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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΑΣ
    -0.07
    šov
    -0.06
    ná
    -0.06
    azel
    -0.06
    очки
    -0.06
    안마
    -0.06
     añ
    -0.06
    ensitive
    -0.06
     Frog
    -0.06
     Javier
    -0.06
    POSITIVE LOGITS
    ||(
    0.08
     pacientes
    0.07
    لل
    0.07
     ngOnInit
    0.07
     onclick
    0.07
     第一
    0.07
     έως
    0.06
     Jackets
    0.06
    ,)↵
    0.06
    .onclick
    0.06
    Act Density 0.001%

    No Known Activations