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

    Neuronpedia

    INDEX
    Explanations

    code/data entries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —if
    -0.08
    	hr
    -0.08
    宜宾
    -0.07
    -hour
    -0.07
    (sr
    -0.07
    fout
    -0.07
    著名的
    -0.07
    ен
    -0.07
    羽毛球
    -0.07
    Թ
    -0.07
    POSITIVE LOGITS
     allocated
    0.07
    locator
    0.07
     yielded
    0.06
    区分
    0.06
     allocations
    0.06
     cooperate
    0.06
     Homeland
    0.06
     Ups
    0.06
    ilig
    0.06
    _Em
    0.06
    Act Density 0.147%

    No Known Activations