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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     huyện
    -0.07
     『
    -0.07
     pathlib
    -0.06
     للس
    -0.06
     flat
    -0.06
     awesome
    -0.06
     fried
    -0.06
     Bib
    -0.06
     plummet
    -0.06
     mensaje
    -0.06
    POSITIVE LOGITS
    rowad
    0.06
    .Id
    0.06
    _memory
    0.06
     drinkers
    0.06
    ührung
    0.06
    employees
    0.06
     collectively
    0.06
    (part
    0.06
    boss
    0.06
    دارة
    0.06
    Act Density 0.000%

    No Known Activations