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

    Neuronpedia

    INDEX
    Explanations

    dependence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     쉽
    -0.07
    以习近平
    -0.06
    锣
    -0.06
     sollten
    -0.06
    뜹
    -0.06
    込まれ
    -0.06
    这也是
    -0.06
    ("$
    -0.06
    风云
    -0.06
    야
    -0.06
    POSITIVE LOGITS
    原来
    0.08
     rotary
    0.08
    inition
    0.08
     ремонт
    0.07
     signage
    0.07
    _Delete
    0.07
    .activate
    0.07
     Burton
    0.07
    illation
    0.07
    .issue
    0.07
    Act Density 0.009%

    No Known Activations