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

    Neuronpedia

    INDEX
    Explanations

    OSI model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    取消
    -0.08
    第一次
    -0.07
    _Font
    -0.06
    Rail
    -0.06
     Magick
    -0.06
    Secondary
    -0.06
     الخاصة
    -0.06
    ійс
    -0.06
     Randolph
    -0.06
    .sec
    -0.06
    POSITIVE LOGITS
     Model
    0.08
    (torch
    0.07
     Models
    0.07
    ']));
    0.07
     orden
    0.06
    maybe
    0.06
     maybe
    0.06
    <Scalars
    0.06
    mentor
    0.06
     OSI
    0.06
    Act Density 0.007%

    No Known Activations