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

    Neuronpedia

    INDEX
    Explanations

    Material Design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vulture
    0.49
    SecurityMarks
    0.49
     troops
    0.48
    hydraz
    0.47
     sobretudo
    0.45
     tjen
    0.45
     eigenvector
    0.45
     బల
    0.45
     paleo
    0.45
     senator
    0.44
    POSITIVE LOGITS
    전
    0.53
    We
    0.51
    You
    0.49
    운
    0.49
    Don
    0.49
     название
    0.48
    Y
    0.48
    RE
    0.47
    Мы
    0.47
    라고
    0.46
    Act Density 0.035%

    No Known Activations