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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quir
    -0.28
    .entries
    -0.27
     kino
    -0.27
    (entries
    -0.27
    ç®´
    -0.27
    ç¾ģ
    -0.25
    çļĦçIJĨæĥ³
    -0.24
    _prefs
    -0.24
    redi
    -0.24
    ä¾µèļĢ
    -0.24
    POSITIVE LOGITS
    çıŃ
    0.28
    Tro
    0.28
    ìŀ¥
    0.25
    å»
    0.25
    box
    0.25
     normally
    0.24
    人åĿĩ
    0.24
    _Box
    0.24
    ä½ľèĢħæīĢæľī
    0.24
     Cy
    0.23
    Act Density 4.212%

    No Known Activations