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

    Neuronpedia

    INDEX
    Explanations

    generate different kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    セス
    0.39
     деца
    0.39
     colaboradores
    0.39
     expresiones
    0.39
     botones
    0.38
     Balfour
    0.38
     Louvre
    0.37
    结论
    0.37
     Avenue
    0.37
     Rover
    0.37
    POSITIVE LOGITS
    queryset
    0.40
     winds
    0.39
     Harm
    0.38
     rains
    0.36
    nar
    0.35
    stopping
    0.35
    mygray
    0.35
    Harm
    0.35
     stopping
    0.35
     Wien
    0.35
    Act Density 0.001%

    No Known Activations