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

    Neuronpedia

    INDEX
    Explanations

    encyclopedic references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蛰
    0.68
     ಲಕ್ಷ
    0.67
     contacts
    0.65
     д
    0.64
     ф
    0.63
     ва
    0.62
     Height
    0.62
     Release
    0.61
     Surge
    0.61
     Contacts
    0.60
    POSITIVE LOGITS
     wikipedia
    1.46
     Britannica
    1.46
     Wikipedia
    1.44
    Wikipedia
    1.31
    britann
    1.29
     encyclopedia
    1.28
     Encyclopedia
    1.24
     wik
    1.23
     Wikip
    1.23
     Вики
    1.22
    Act Density 0.107%

    No Known Activations