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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PC
    -0.06
     Protection
    -0.06
    -al
    -0.06
    .questions
    -0.05
    -Le
    -0.05
    安
    -0.05
     commission
    -0.05
     Et
    -0.05
     conoc
    -0.05
     Car
    -0.05
    POSITIVE LOGITS
    ']?>"
    0.07
     الوطني
    0.07
    ۱۹۹
    0.07
    Dream
    0.07
    없음
    0.07
    the
    0.07
    Stretch
    0.07
     }}↵↵
    0.07
    …the
    0.06
    Tables
    0.06
    Act Density 0.012%

    No Known Activations