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

    Neuronpedia

    INDEX
    Explanations

    Prepositions and "that"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ruit
    -0.07
     Offset
    -0.07
     ///
    -0.07
    ास
    -0.07
     Canada
    -0.07
     себе
    -0.07
    [code
    -0.07
    俄
    -0.06
    _estimate
    -0.06
    此
    -0.06
    POSITIVE LOGITS
     kter
    0.07
     улучш
    0.06
    SACTION
    0.06
    Ы
    0.06
     buluş
    0.06
    otoxic
    0.06
     ин
    0.06
     Marlins
    0.06
    .icons
    0.06
    bc
    0.05
    Act Density 0.506%

    No Known Activations