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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (identity
    -0.07
    probability
    -0.07
    .Request
    -0.07
    Blur
    -0.06
    .clear
    -0.06
    {return
    -0.06
    college
    -0.06
    ежать
    -0.06
    选择
    -0.06
    Marc
    -0.06
    POSITIVE LOGITS
     Εκ
    0.07
     rural
    0.07
    utory
    0.07
     irq
    0.06
    =>
    0.06
     스타
    0.06
    ِه
    0.06
     경북
    0.06
    sex
    0.06
     companions
    0.06
    Act Density 0.101%

    No Known Activations