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

    Neuronpedia

    INDEX
    Explanations

    famous sentences or openings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fNil
    0.35
    fireFlower
    0.34
     trycatch
    0.33
    BleStatus
    0.33
     offsetX
    0.33
    ามารถ
    0.32
    梼
    0.32
    ActionsForRule
    0.32
    莳
    0.32
    ヤモンド
    0.32
    POSITIVE LOGITS
    -
    0.45
    ↵
    0.43
    ,
    0.37
    '
    0.37
    7
    0.36
    ’
    0.35
     -
    0.34
     &
    0.33
    T
    0.33
    |
    0.33
    Act Density 0.001%

    No Known Activations