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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gorges
    0.69
    ನನ್ನು
    0.53
     peroneal
    0.52
     reservoirs
    0.52
     sabotage
    0.52
     pallets
    0.51
     moons
    0.51
     الساعة
    0.51
     왜
    0.51
    ರನ್ನು
    0.51
    POSITIVE LOGITS
    9
    0.79
    6
    0.73
    4
    0.73
    7
    0.73
    TO
    0.71
    8
    0.70
    5
    0.70
    I
    0.68
    0
    0.66
    O
    0.66
    Act Density 0.033%

    No Known Activations