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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touch
    -0.08
    isman
    -0.07
     Hatch
    -0.07
    董事
    -0.07
     TU
    -0.07
     Expense
    -0.07
    笑
    -0.07
    達到
    -0.06
     chanting
    -0.06
     запрос
    -0.06
    POSITIVE LOGITS
    Occup
    0.08
    服役
    0.07
    メリ
    0.07
    剩余
    0.07
    .IsNull
    0.07
     yerleş
    0.06
    _decay
    0.06
     usable
    0.06
    筛选
    0.06
    brid
    0.06
    Act Density 0.500%

    No Known Activations