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

    Neuronpedia

    INDEX
    Explanations

    going, coming, heading, returning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    現在は
    0.45
    currently
    0.43
     beschäftigt
    0.40
     dada
    0.38
     प्रशास
    0.38
     currently
    0.38
    gebra
    0.37
     součas
    0.36
    operate
    0.36
     कार्यरत
    0.36
    POSITIVE LOGITS
     joining
    1.04
     entering
    1.00
     retiring
    0.97
     going
    0.96
     returning
    0.94
     Going
    0.91
    Going
    0.91
     coming
    0.87
     Returning
    0.86
    returning
    0.84
    Act Density 0.013%

    No Known Activations