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

    Neuronpedia

    INDEX
    Explanations

    driving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .same
    -0.09
     Adresse
    -0.07
    _delta
    -0.07
    んで
    -0.07
    当然是
    -0.07
    .gender
    -0.07
     regards
    -0.07
    常识
    -0.07
    照顾
    -0.06
     $↵↵
    -0.06
    POSITIVE LOGITS
    ウォ
    0.07
    =(-
    0.07
    pNet
    0.07
     efficient
    0.07
    國
    0.06
     Salt
    0.06
    -ste
    0.06
    строен
    0.06
    @Autowired
    0.06
     optarg
    0.06
    Act Density 0.181%

    No Known Activations