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

    Neuronpedia

    INDEX
    Explanations

    basic HTML and CSS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boat
    0.43
     竹
    0.40
     statunitense
    0.39
     )।
    0.39
    ⱼ
    0.39
    Terr
    0.38
    sail
    0.38
     maximize
    0.38
     zuerst
    0.38
    =[
    0.37
    POSITIVE LOGITS
     committing
    0.40
     соединения
    0.40
    échange
    0.40
     Conn
    0.40
     decorated
    0.38
     application
    0.37
     div
    0.37
    orge
    0.37
     Mont
    0.37
     gels
    0.35
    Act Density 0.000%

    No Known Activations