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

    Neuronpedia

    INDEX
    Explanations

    error messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    五大
    -0.08
    Exception
    -0.07
    炸弹
    -0.07
    icional
    -0.07
    翮
    -0.07
     Jon
    -0.07
     JOptionPane
    -0.07
    character
    -0.07
    敵
    -0.06
    ליל
    -0.06
    POSITIVE LOGITS
    ﹏
    0.09
    弛
    0.07
    峱
    0.07
    QA
    0.07
    PEED
    0.06
    滑
    0.06
    找回
    0.06
    骃
    0.06
    {j
    0.06
     straps
    0.06
    Act Density 0.006%

    No Known Activations