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

    Neuronpedia

    INDEX
    Explanations

    options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pioneered
    -0.08
     znám
    -0.08
    .pp
    -0.08
    Planet
    -0.08
    Triggers
    -0.08
     retrouvé
    -0.08
     ਰਹ
    -0.07
     ಅವರನ್ನು
    -0.07
     wodurch
    -0.07
    Detector
    -0.07
    POSITIVE LOGITS
     numbered
    0.11
    编号
    0.09
    .options
    0.09
     विकल्प
    0.08
    作文
    0.08
     apt
    0.08
     JLabel
    0.08
     Boolean
    0.08
     Davis
    0.08
     Yes
    0.08
    Act Density 0.039%

    No Known Activations