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

    Neuronpedia

    INDEX
    Explanations

    Power Supply, typos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foothills
    0.50
     versatility
    0.46
     ergonom
    0.45
     scouring
    0.45
     சுற்றுச்சூழ
    0.44
     utilizza
    0.44
     hiking
    0.43
     contoured
    0.43
     kayaking
    0.43
     bioactive
    0.42
    POSITIVE LOGITS
    公寓
    0.43
    宿舍
    0.42
    Citizens
    0.41
     sindical
    0.41
     millioner
    0.40
    Commission
    0.39
     अदालत
    0.39
     dormitory
    0.38
     celebrado
    0.38
    UNDO
    0.38
    Act Density 0.004%

    No Known Activations