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

    Neuronpedia

    INDEX
    Explanations

    variable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    відом
    -0.07
    ician
    -0.07
    names
    -0.07
    าข
    -0.06
    oded
    -0.06
    CAM
    -0.06
    ITTE
    -0.06
    ‌د
    -0.06
    '],$_
    -0.06
    縮
    -0.06
    POSITIVE LOGITS
     склад
    0.07
     marrow
    0.07
    ty
    0.07
     shortest
    0.07
    iteral
    0.06
     Mass
    0.06
     cyclists
    0.06
     DPI
    0.06
     Concord
    0.06
    -nil
    0.06
    Act Density 0.016%

    No Known Activations