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

    Neuronpedia

    INDEX
    Explanations

    Research/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -described
    -0.07
     BitSet
    -0.06
    ovaný
    -0.06
     nurture
    -0.06
     childs
    -0.06
     Champion
    -0.06
     granddaughter
    -0.06
    -white
    -0.06
    fields
    -0.06
     assistant
    -0.06
    POSITIVE LOGITS
     }.
    0.06
    ongodb
    0.06
    %);↵
    0.06
     gew
    0.06
    .Emit
    0.06
    /react
    0.06
     collar
    0.06
     볼
    0.06
     accum
    0.06
    }↵
    0.06
    Act Density 0.000%

    No Known Activations