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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stored
    -0.08
     homo
    -0.08
     ===
    -0.08
    TreeNode
    -0.07
     censor
    -0.07
     кноп
    -0.07
    WindowState
    -0.07
    "You
    -0.07
     responseObject
    -0.07
    :new
    -0.07
    POSITIVE LOGITS
    5
    0.17
    05
    0.12
    ۵
    0.11
     five
    0.10
    五
    0.10
    3
    0.09
    55
    0.09
    6
    0.09
     Five
    0.08
     五
    0.08
    Act Density 0.387%

    No Known Activations