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

    Neuronpedia

    INDEX
    Explanations

    probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Measurement
    -0.07
    ается
    -0.07
     Santa
    -0.06
     ве
    -0.06
     decreasing
    -0.06
    เซ
    -0.06
    ñas
    -0.06
     Vil
    -0.06
     Haley
    -0.06
    ,title
    -0.06
    POSITIVE LOGITS
    donnees
    0.07
    navigator
    0.06
     PTR
    0.06
     наблюд
    0.06
    男子
    0.06
             
    0.06
    ToObject
    0.06
    isoner
    0.06
    shutdown
    0.06
     astronom
    0.06
    Act Density 0.002%

    No Known Activations