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

    Neuronpedia

    INDEX
    Explanations

    timeframes and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     సహ
    0.67
     बेव
    0.64
    extended
    0.62
     зат
    0.61
    expose
    0.60
    planning
    0.59
     hazırl
    0.58
    ervices
    0.58
    ismatch
    0.58
    familiar
    0.58
    POSITIVE LOGITS
    饵
    0.87
     floss
    0.86
     carburetor
    0.81
    bagai
    0.79
     lace
    0.78
    ва
    0.78
    สดง
    0.77
    StartX
    0.77
     impres
    0.77
    ওল
    0.76
    Act Density 0.067%

    No Known Activations