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

    Neuronpedia

    INDEX
    Explanations

    mass displacement movements media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.61
     a
    0.57
     যাবতীয়
    0.56
    ۲
    0.51
    обе
    0.50
    components
    0.48
    ə
    0.48
    ем
    0.48
    riere
    0.47
    ین
    0.47
    POSITIVE LOGITS
     mass
    0.91
     bulk
    0.85
    achusetts
    0.71
    批量
    0.71
     массо
    0.66
     massa
    0.65
    bulk
    0.65
    VOLUME
    0.63
     Bulk
    0.61
     масса
    0.60
    Act Density 0.060%

    No Known Activations