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

    Neuronpedia

    INDEX
    Explanations

    avoiding ai detection and plagiarism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diseg
    0.46
     desenho
    0.43
     objets
    0.43
     desenhos
    0.42
    DWARF
    0.42
    vm
    0.42
    spotify
    0.41
     potentiometer
    0.41
     BUG
    0.41
     teint
    0.41
    POSITIVE LOGITS
     Essay
    0.92
    Essay
    0.87
    essay
    0.87
     essay
    0.85
     Writing
    0.83
     Academic
    0.82
    写作
    0.82
    Academic
    0.81
     plagiarism
    0.80
     Essays
    0.79
    Act Density 0.007%

    No Known Activations