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

    Neuronpedia

    INDEX
    Explanations

    take with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surrounding
    0.45
     proximate
    0.45
     neighboring
    0.44
     сосед
    0.43
     adjacent
    0.42
     surrounded
    0.41
     lineup
    0.41
    कभी
    0.41
    Neighbor
    0.40
    配信
    0.40
    POSITIVE LOGITS
     consigo
    1.55
     contigo
    1.30
     conmigo
    1.22
     comigo
    1.15
     معه
    1.04
     معك
    1.03
     along
    0.98
     साथ
    0.92
     Along
    0.91
     معكم
    0.87
    Act Density 0.011%

    No Known Activations