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

    Neuronpedia

    INDEX
    Explanations

    intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Powerful
    0.88
     poderosa
    0.86
     intensa
    0.85
     Powerful
    0.84
     potente
    0.83
    Elegant
    0.78
     Elegant
    0.78
     poderoso
    0.77
     puiss
    0.77
    骜
    0.77
    POSITIVE LOGITS
     quite
    2.10
     very
    1.73
    quite
    1.72
     довольно
    1.66
     somewhat
    1.60
     очень
    1.57
     весьма
    1.56
    Quite
    1.52
     Quite
    1.51
     pretty
    1.47
    Act Density 0.435%

    No Known Activations