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

    Neuronpedia

    INDEX
    Explanations

    clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    맆
    -0.08
    妧
    -0.08
    _min
    -0.08
    ibt
    -0.07
    (success
    -0.07
    ﰢ
    -0.07
    享
    -0.07
    leşme
    -0.07
    隨
    -0.07
    쒀
    -0.06
    POSITIVE LOGITS
     Production
    0.08
    clin
    0.08
    接纳
    0.07
    leys
    0.07
     patio
    0.07
    промышлен
    0.07
     oppos
    0.07
     eject
    0.07
    .MessageBox
    0.07
     knockout
    0.07
    Act Density 0.046%

    No Known Activations