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

    Neuronpedia

    INDEX
    Explanations

    best text match

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     વડે
    0.41
     Прави
    0.40
    helia
    0.39
    beacon
    0.38
     Utils
    0.37
    entuan
    0.37
    onio
    0.36
     Saclay
    0.36
     давление
    0.35
     போக்கு
    0.35
    POSITIVE LOGITS
     hide
    0.40
    τισ
    0.39
    resultlist
    0.38
     umpire
    0.38
    おすすめ
    0.37
     culture
    0.37
     documentaries
    0.36
     invisibility
    0.36
     hid
    0.36
     illusory
    0.35
    Act Density 0.000%

    No Known Activations