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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <+
    -0.07
    >
    -0.07
    plementary
    -0.06
     aggregates
    -0.06
     кла
    -0.06
    แม
    -0.06
    •
    -0.06
    葡
    -0.06
    _trial
    -0.06
     cafe
    -0.06
    POSITIVE LOGITS
    です
    0.07
    řes
    0.06
    (weather
    0.06
    lomou
    0.06
    (common
    0.06
    كرة
    0.06
     rap
    0.06
    。一
    0.06
    -buy
    0.06
     relação
    0.06
    Act Density 0.025%

    No Known Activations