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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     January
    -0.07
    .presentation
    -0.07
    隐
    -0.07
    Excellent
    -0.06
     για
    -0.06
     November
    -0.06
    Think
    -0.06
    Worksheet
    -0.06
    альних
    -0.06
     Gather
    -0.06
    POSITIVE LOGITS
     mL
    0.06
    _book
    0.06
    iazza
    0.06
     Kia
    0.06
     لی
    0.06
     cm
    0.06
     cords
    0.06
    _lab
    0.06
     frames
    0.05
     oranges
    0.05
    Act Density 0.033%

    No Known Activations