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

    Neuronpedia

    INDEX
    Explanations

    Person of Interest TV show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     आदि
    -0.08
     डाय
    -0.07
     पॉ
    -0.07
    /re
    -0.07
     twice
    -0.07
     fleeting
    -0.07
     rough
    -0.07
     Fol
    -0.07
     र
    -0.07
     रे
    -0.07
    POSITIVE LOGITS
     исти
    0.08
    :Int
    0.08
     wagers
    0.08
    :num
    0.08
     Entscheidungen
    0.08
     Egal
    0.08
     независ
    0.08
    Courtesy
    0.08
     توافق
    0.08
     obedient
    0.08
    Act Density 0.000%

    No Known Activations