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

    Neuronpedia

    INDEX
    Explanations

    spatial locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Agencia
    0.38
    篒
    0.37
     मेघा
    0.36
     advogado
    0.36
    лянчук
    0.35
     financiero
    0.35
    考える
    0.34
    貳
    0.34
     सकुशल
    0.34
     ませ
    0.34
    POSITIVE LOGITS
     sides
    1.03
     bottom
    1.02
     edges
    0.97
    bottom
    0.94
     upper
    0.94
     underside
    0.93
     top
    0.92
     corners
    0.92
     front
    0.91
    底部
    0.88
    Act Density 0.111%

    No Known Activations