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

    Neuronpedia

    INDEX
    Explanations

    greeting and welcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sorry
    0.50
    sorry
    0.45
     Thank
    0.44
    Thank
    0.40
    primarily
    0.40
    ඈ
    0.40
    Sorry
    0.40
     Enjoy
    0.39
    ematic
    0.39
     erro
    0.39
    POSITIVE LOGITS
    вшиеся
    0.47
    вшийся
    0.46
     хорошие
    0.44
     చెప్పు
    0.44
     flashbacks
    0.42
     kenapa
    0.41
     Afternoon
    0.40
     दोपहर
    0.40
     proteção
    0.40
     warships
    0.39
    Act Density 0.007%

    No Known Activations