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

    Neuronpedia

    INDEX
    Explanations

    Figure references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Div
    -0.08
    .search
    -0.07
     zijn
    -0.07
    Dear
    -0.06
     sauce
    -0.06
    .reshape
    -0.06
    legacy
    -0.06
    _triangle
    -0.06
    .Team
    -0.06
    .Description
    -0.06
    POSITIVE LOGITS
    ीतर
    0.06
    usk
    0.06
     只
    0.06
    ورت
    0.06
     т
    0.06
     Vi
    0.06
    、《
    0.06
     stratej
    0.06
    >r
    0.06
     collects
    0.06
    Act Density 0.004%

    No Known Activations