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

    Neuronpedia

    INDEX
    Explanations

    outside bounds, Norway, fur, eyes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    H
    0.48
     H
    0.44
     Beruf
    0.41
    不得不
    0.40
     이라고
    0.39
     Surv
    0.38
     noteworthy
    0.38
     ہ
    0.37
    ందన్నారు
    0.37
     λοι
    0.37
    POSITIVE LOGITS
    rahydro
    0.46
    la
    0.45
    这样
    0.45
    one
    0.45
    פי
    0.45
    ่
    0.45
    しやすい
    0.43
    foods
    0.42
    than
    0.41
    as
    0.41
    Act Density 0.011%

    No Known Activations