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

    Neuronpedia

    INDEX
    Explanations

    that followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Act
    0.67
    contains
    0.66
    act
    0.65
     berisi
    0.61
     содержит
    0.60
     misalkan
    0.60
     использует
    0.60
    acts
    0.58
    ارا
    0.57
    not
    0.57
    POSITIVE LOGITS
     permeates
    0.90
     permeate
    0.89
     plagues
    0.88
     characterize
    0.88
     such
    0.88
     myriad
    0.87
     characterizes
    0.87
     perv
    0.84
     pandemics
    0.83
     every
    0.82
    Act Density 0.028%

    No Known Activations