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

    Neuronpedia

    INDEX
    Explanations

    principles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nets
    -0.31
     splice
    -0.27
    splice
    -0.27
    iface
    -0.27
    åĻ¨
    -0.27
    书
    -0.26
     page
    -0.25
     book
    -0.25
    .SizeF
    -0.25
    éĿ¢è²Į
    -0.25
    POSITIVE LOGITS
    /gtest
    0.28
    èįīæ¡Ī
    0.24
    åĪijäºĭ
    0.24
     Titan
    0.24
    besch
    0.23
    åĨ·èĹı
    0.23
    è¦ģçĤ¹
    0.23
    ellular
    0.23
    openh
    0.23
    Leaks
    0.23
    Act Density 0.018%

    No Known Activations