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

    Neuronpedia

    INDEX
    Explanations

    this is or includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Щ
    0.60
     Таким
    0.57
    those
    0.56
    ów
    0.56
    ت
    0.54
     एवं
    0.54
    érieures
    0.53
     অন্যান্য
    0.53
    Similarly
    0.53
    autres
    0.53
    POSITIVE LOGITS
     isn
    1.29
     is
    1.29
     happens
    1.17
     gives
    1.08
     seems
    1.07
     represents
    1.06
     involves
    1.06
     creates
    1.05
     demonstrates
    1.04
     doesn
    1.04
    Act Density 0.637%

    No Known Activations