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

    Neuronpedia

    INDEX
    Explanations

    Uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Compassion
    -0.08
     wenige
    -0.08
     compassion
    -0.08
     peroxide
    -0.07
    mäß
    -0.07
     परेश
    -0.07
    (Config
    -0.07
    (Reg
    -0.07
     госп
    -0.07
    ところ
    -0.07
    POSITIVE LOGITS
     bedoeld
    0.09
     предназнач
    0.09
     evolutionary
    0.09
     representam
    0.09
     meant
    0.08
     abbreviation
    0.08
     abbrevi
    0.08
    用于
    0.08
    对应
    0.08
     representan
    0.08
    Act Density 0.069%

    No Known Activations