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

    Neuronpedia

    INDEX
    Explanations

    relativity of simultaneity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ruth
    0.57
    Bought
    0.55
    Trich
    0.55
    Gina
    0.52
    Everyone
    0.51
    Neha
    0.50
    Love
    0.49
    Press
    0.48
    Will
    0.48
    Simone
    0.47
    POSITIVE LOGITS
     nearby
    0.48
    brace
    0.47
     경로
    0.47
     {$
    0.46
     근
    0.45
     full
    0.45
     remote
    0.45
     Remote
    0.45
    subseteq
    0.44
     Operational
    0.43
    Act Density 0.000%

    No Known Activations