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

    Neuronpedia

    INDEX
    Explanations

    panel discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -1.54
     unmöglich
    -1.41
    ↵
    -1.38
    两个
    -1.28
    曷
    -1.25
     ersten
    -1.24
     Geografia
    -1.24
    şik
    -1.20
     isnt
    -1.20
    ffiti
    -1.17
    POSITIVE LOGITS
    ters
    1.47
    R
    1.46
    事で
    1.36
     convertView
    1.34
    vail
    1.34
    lieving
    1.32
    ????????
    1.30
    C
    1.30
    ﾏ
    1.28
    transQ
    1.27
    Act Density 0.032%

    No Known Activations