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

    Neuronpedia

    INDEX
    Explanations

    to-do lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orton
    0.45
    ョン
    0.38
     autón
    0.38
    acus
    0.38
     silenc
    0.36
    aina
    0.35
     silic
    0.35
    ュ
    0.35
    ង
    0.35
     कांस्टेबल
    0.35
    POSITIVE LOGITS
     Todo
    1.44
    Todo
    1.39
     todo
    1.36
     TODO
    1.33
    ToDo
    1.29
    todo
    1.26
    TODO
    1.20
    TodoList
    1.12
     checklist
    1.09
    todos
    1.08
    Act Density 0.047%

    No Known Activations