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

    Neuronpedia

    INDEX
    Explanations

    difficulty rating, seamless construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     police
    0.50
     after
    0.48
     recreation
    0.44
    ژ
    0.43
     leisure
    0.43
     Police
    0.43
     polici
    0.43
     southwest
    0.43
     indoors
    0.42
    ,
    0.42
    POSITIVE LOGITS
     하나님의
    0.47
    ରେ
    0.47
    RawO
    0.47
    比较
    0.46
    fühl
    0.46
     belangrijke
    0.45
    天然
    0.44
     하나님
    0.44
    ากหลาย
    0.44
     Accountability
    0.43
    Act Density 0.007%

    No Known Activations