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

    Neuronpedia

    INDEX
    Explanations

    28

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     方法
    -0.07
     Unable
    -0.07
     lines
    -0.06
    (Thread
    -0.06
     komunik
    -0.06
    Append
    -0.06
    ğimiz
    -0.06
     jes
    -0.06
    opic
    -0.06
     公司
    -0.06
    POSITIVE LOGITS
    _traj
    0.06
    ㅇ
    0.06
     امن
    0.06
    ilin
    0.06
    اجه
    0.06
    _hidden
    0.06
    引用
    0.06
     smith
    0.06
    fld
    0.06
     �
    0.06
    Act Density 0.005%

    No Known Activations