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

    Neuronpedia

    INDEX
    Explanations

    puzzle and riddle contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invoice
    0.39
    SalesRep
    0.38
    мов
    0.36
     সমুদ
    0.36
     सीआर
    0.36
     stakeholders
    0.35
     Comcast
    0.35
    事業
    0.34
     comorbidities
    0.34
     invoicing
    0.34
    POSITIVE LOGITS
     puzzle
    1.73
     puzzles
    1.73
     solving
    1.62
    Puzzle
    1.59
     Solving
    1.55
     Puzzle
    1.55
     solve
    1.50
    puzzle
    1.49
    Solving
    1.46
     solved
    1.45
    Act Density 0.087%

    No Known Activations