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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nghiêm
    -0.07
    َك
    -0.07
     McCabe
    -0.07
    'D
    -0.07
     meanwhile
    -0.07
     durch
    -0.07
    									↵
    -0.07
     insulting
    -0.06
    \\
    -0.06
    (duration
    -0.06
    POSITIVE LOGITS
    аз
    0.07
    وت
    0.06
     oracle
    0.06
     заказ
    0.06
    _PAR
    0.06
    using
    0.06
    EDURE
    0.06
    ceive
    0.06
     savings
    0.06
    _cycles
    0.06
    Act Density 0.000%

    No Known Activations