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

    Neuronpedia

    INDEX
    Explanations

    contact numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    0.43
     you
    0.43
     if
    0.42
     WHERE
    0.41
     u
    0.40
     Eric
    0.40
     And
    0.40
     Bill
    0.40
     dan
    0.40
     rest
    0.39
    POSITIVE LOGITS
    ╽
    0.50
    知県
    0.44
    震撼
    0.41
    égio
    0.41
    ၜ
    0.40
    暠
    0.40
    udarstven
    0.40
    ؒ
    0.40
    pidos
    0.39
    umbia
    0.39
    Act Density 0.001%

    No Known Activations