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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proclaim
    -0.07
     heartbeat
    -0.07
     Ski
    -0.06
    共产
    -0.06
    bildung
    -0.06
    .usage
    -0.06
    健全
    -0.06
     OTP
    -0.06
     Considering
    -0.06
    .algorithm
    -0.06
    POSITIVE LOGITS
    \',
    0.09
    %'
    0.08
    @Setter
    0.07
    _Interface
    0.07
    故事
    0.07
    笳
    0.07
    .addActionListener
    0.07
    啤酒
    0.07
    ⁎
    0.07
     Es
    0.07
    Act Density 0.007%

    No Known Activations