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

    Neuronpedia

    INDEX
    Explanations

    locations near other locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    与之
    0.83
     그다
    0.77
     напрямую
    0.75
     Directly
    0.74
     అన్ని
    0.72
     directly
    0.71
     সরাস
    0.71
    ല്ലാം
    0.70
    衽
    0.69
    下一
    0.69
    POSITIVE LOGITS
     near
    2.98
    near
    2.68
     Near
    2.55
    Near
    2.53
     NEAR
    1.89
     northeast
    1.86
     southeast
    1.79
    NEAR
    1.78
     south
    1.77
     north
    1.73
    Act Density 0.078%

    No Known Activations