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

    Neuronpedia

    INDEX
    Explanations

    discussion and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hostels
    0.49
     mottled
    0.46
     coriander
    0.46
     ateliers
    0.46
     necrosis
    0.45
     sexes
    0.45
     leaflets
    0.45
     blots
    0.44
     gloves
    0.44
     souvenirs
    0.44
    POSITIVE LOGITS
     Assignment
    0.64
     задание
    0.62
     Module
    0.61
     assignment
    0.56
    Assignment
    0.54
     Kaltura
    0.54
    Module
    0.54
     Virtual
    0.53
     Week
    0.51
     Click
    0.50
    Act Density 0.030%

    No Known Activations