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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monitoring
    -0.08
    .JTextField
    -0.06
     데
    -0.06
     exceptional
    -0.06
     Mel
    -0.06
     jTextField
    -0.06
     blog
    -0.06
     Chim
    -0.06
     Brushes
    -0.06
     monitoring
    -0.06
    POSITIVE LOGITS
     川
    0.07
    =all
    0.07
    BUG
    0.07
     داد
    0.06
    lobber
    0.06
     تصم
    0.06
    aceous
    0.06
     Gutenberg
    0.06
    ukkit
    0.06
     absol
    0.06
    Act Density 0.017%

    No Known Activations