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

    Neuronpedia

    INDEX
    Explanations

    cleaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rych
    -0.06
            ↵        ↵        ↵
    -0.06
     المف
    -0.06
    Fly
    -0.06
    <HashMap
    -0.06
    ським
    -0.06
     sécur
    -0.06
    stored
    -0.06
    هدف
    -0.06
     مشهد
    -0.06
    POSITIVE LOGITS
     INTERFACE
    0.07
    need
    0.07
    _balance
    0.07
     tidy
    0.06
     exig
    0.06
    usto
    0.06
     chemicals
    0.06
    wine
    0.06
     Tail
    0.06
     Manual
    0.06
    Act Density 0.012%

    No Known Activations