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

    Neuronpedia

    INDEX
    Explanations

    expressing relationships and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cập
    -0.06
     lief
    -0.06
     doğal
    -0.06
    orted
    -0.06
    /tutorial
    -0.06
     Pivot
    -0.06
    (urls
    -0.06
     naprost
    -0.06
     घर
    -0.06
    ierten
    -0.06
    POSITIVE LOGITS
     Baz
    0.07
    UCT
    0.06
     creators
    0.06
     Outputs
    0.06
    unitOfWork
    0.06
    ndon
    0.06
    brightness
    0.06
    two
    0.06
     communal
    0.06
    歲
    0.06
    Act Density 0.282%

    No Known Activations