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

    Neuronpedia

    INDEX
    Explanations

    twitter links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Instagram
    0.43
    https
    0.42
     Medan
    0.38
     계
    0.38
     LinkedIn
    0.38
    Repost
    0.37
     repost
    0.37
    ヴァ
    0.37
     Rep
    0.36
    ڤ
    0.36
    POSITIVE LOGITS
    勺
    0.44
    ாய்ச்ச
    0.40
    きた
    0.40
     alcanzar
    0.39
    いきます
    0.39
     кою
    0.39
    Unifier
    0.39
     Итак
    0.38
    ख्य
    0.38
    conform
    0.38
    Act Density 0.003%

    No Known Activations