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

    Neuronpedia

    INDEX
    Explanations

    evaluating specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VALUES
    0.39
     약
    0.38
     ทีม
    0.38
    약
    0.38
    䣷
    0.38
    iklet
    0.37
    约
    0.37
    秇
    0.37
    ⛷
    0.37
    학생
    0.36
    POSITIVE LOGITS
    arctica
    0.41
     database
    0.39
    database
    0.38
     Datenbank
    0.38
    ermat
    0.37
     warrants
    0.37
    ૨
    0.37
     electrical
    0.36
    렌
    0.36
     E
    0.36
    Act Density 0.000%

    No Known Activations