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

    Neuronpedia

    INDEX
    Explanations

    adding items to collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     setShow
    0.43
    ungkinan
    0.42
     അമ്മ
    0.40
    Setting
    0.39
    CharacterSet
    0.39
    hydrogen
    0.38
    😭😭
    0.38
    Sorting
    0.38
     motherhood
    0.38
     lágrimas
    0.38
    POSITIVE LOGITS
    add
    0.59
     add
    0.57
     discard
    0.53
    discard
    0.48
     intersection
    0.48
     union
    0.46
    adds
    0.46
    intersection
    0.45
     Add
    0.44
     adds
    0.43
    Act Density 0.005%

    No Known Activations