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

    Neuronpedia

    INDEX
    Explanations

    this/self (programming)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pedido
    -0.08
    柿
    -0.07
    第三节
    -0.07
    毛泽
    -0.06
    )==
    -0.06
     Roll
    -0.06
    酆
    -0.06
     максималь
    -0.06
    八十
    -0.06
     flee
    -0.06
    POSITIVE LOGITS
     SCORE
    0.08
    \_
    0.07
     vẽ
    0.07
    饩
    0.07
    办公
    0.07
     Selection
    0.07
     needed
    0.07
     sẽ
    0.06
    醫生
    0.06
    死亡
    0.06
    Act Density 0.035%

    No Known Activations