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

    Neuronpedia

    INDEX
    Explanations

    programming arguments and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     letter
    -0.07
    兩
    -0.07
     Observatory
    -0.07
    负责
    -0.07
    Zombie
    -0.07
    /AIDS
    -0.07
    él
    -0.07
    isering
    -0.07
     rekom
    -0.07
    成熟
    -0.07
    POSITIVE LOGITS
     nargs
    0.12
    	args
    0.10
    _args
    0.10
     args
    0.10
    args
    0.10
     arguments
    0.09
    Args
    0.09
     invocation
    0.09
    .arguments
    0.09
    _arguments
    0.09
    Act Density 0.008%

    No Known Activations