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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glazing
    -0.08
    认可
    -0.08
    Dat
    -0.07
    |
    -0.07
    -0.07
    Ig
    -0.07
    留
    -0.07
     Ig
    -0.07
    בו
    -0.07
    IBA
    -0.07
    POSITIVE LOGITS
     Wey
    0.09
     Thus
    0.08
     Wrest
    0.08
     "*"
    0.08
     따라서
    0.08
     cabinets
    0.07
     Conservatives
    0.07
    pard
    0.07
     همچنین
    0.07
    なので
    0.07
    Act Density 0.033%
    No Known Activations