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

    Neuronpedia

    INDEX
    Explanations

    average/mean computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Сам
    -0.09
     Armstrong
    -0.08
    Сам
    -0.08
     formally
    -0.08
    주세요
    -0.08
     сама
    -0.07
    يوس
    -0.07
     actualidad
    -0.07
    ാർത്ഥ
    -0.07
    حدث
    -0.07
    POSITIVE LOGITS
     unnoticed
    0.09
     ছিল
    0.08
    0.08
    wet
    0.08
    �
    0.08
     હતું
    0.07
    cludes
    0.07
     noto
    0.07
     pulses
    0.07
    -il
    0.07
    Act Density 0.065%
    No Known Activations