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

    Neuronpedia

    INDEX
    Explanations

    offering another riddle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personnal
    0.76
    ﺧ
    0.74
     우선
    0.73
     personalmente
    0.71
     personalised
    0.69
     customise
    0.69
     primarily
    0.68
    Customize
    0.68
    Retrieve
    0.68
     priority
    0.67
    POSITIVE LOGITS
    solved
    0.97
     solving
    0.94
    solving
    0.94
     another
    0.93
    Another
    0.93
     solved
    0.90
    Puzzle
    0.90
     puzz
    0.89
    another
    0.88
     puzzles
    0.87
    Act Density 0.031%

    No Known Activations