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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    是多少
    -0.08
     रखना
    -0.08
    �
    -0.08
     premio
    -0.08
     해야
    -0.08
     المث
    -0.08
     하는
    -0.07
    ใหม่
    -0.07
    �
    -0.07
    ätzen
    -0.07
    POSITIVE LOGITS
     worse
    0.13
     awful
    0.12
     Worse
    0.12
     негатив
    0.11
     wors
    0.11
     negativ
    0.10
     horrible
    0.10
     terrible
    0.10
     ухуд
    0.10
     peor
    0.10
    Act Density 0.226%

    No Known Activations