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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ัตถ
    -0.07
     IMDb
    -0.07
    ुं
    -0.07
     आख
    -0.06
    ۵۰
    -0.06
    -centric
    -0.06
    safe
    -0.06
     프
    -0.06
     iets
    -0.06
     väl
    -0.06
    POSITIVE LOGITS
    <unsigned
    0.06
    deo
    0.06
     Grat
    0.06
    -follow
    0.06
    foto
    0.06
     Origins
    0.06
     replica
    0.06
    چ
    0.06
    _process
    0.06
     list
    0.06
    Act Density 0.000%

    No Known Activations