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

    Neuronpedia

    INDEX
    Explanations

    continued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pos
    -0.07
    ccording
    -0.07
    Você
    -0.07
    有意思
    -0.07
    _Act
    -0.07
    缴纳
    -0.07
    QS
    -0.07
    ΄
    -0.07
    .top
    -0.07
     เมษายน
    -0.07
    POSITIVE LOGITS
     potentials
    0.08
    杀了
    0.07
    asted
    0.07
    况
    0.07
    ptime
    0.07
    _disk
    0.07
     Novel
    0.07
    롑
    0.06
     histories
    0.06
    adapter
    0.06
    Act Density 0.004%

    No Known Activations