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

    Neuronpedia

    INDEX
    Explanations

    SQL keywords and database commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     관리
    0.53
     জানিয়ে
    0.45
     работода
    0.43
    managed
    0.42
     MANAG
    0.42
     CONTRIBUT
    0.40
     hasattr
    0.40
     ওয়েবসাইট
    0.39
    דה
    0.39
     प्रबंधक
    0.39
    POSITIVE LOGITS
     lasso
    0.47
    MovementControls
    0.46
     lasers
    0.44
     gods
    0.43
    ANSI
    0.43
     neurons
    0.43
     misdemean
    0.42
     cruisers
    0.42
     bei
    0.42
     neutrons
    0.42
    Act Density 0.004%

    No Known Activations