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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    補
    -0.07
     DN
    -0.07
     takové
    -0.06
     Kore
    -0.06
     เซ
    -0.06
     物
    -0.06
    щин
    -0.06
     Champion
    -0.06
     notre
    -0.06
     ions
    -0.06
    POSITIVE LOGITS
    ška
    0.07
     умер
    0.06
    IsValid
    0.06
    tréal
    0.06
    Ž
    0.06
    patibility
    0.06
    aroo
    0.06
    (public
    0.06
     skips
    0.06
    |unique
    0.06
    Act Density 0.013%

    No Known Activations