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

    Neuronpedia

    INDEX
    Explanations

    always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     결정
    0.44
    贻
    0.43
    سترول
    0.42
    ardı
    0.42
    وریت
    0.42
    名前
    0.41
    讹
    0.41
    ید
    0.41
    اری
    0.41
    厢
    0.41
    POSITIVE LOGITS
    rad
    0.47
    st
    0.46
    job
    0.44
     boils
    0.44
     verko
    0.43
    ins
    0.42
    bus
    0.42
     we
    0.42
     apaixon
    0.42
     bequem
    0.42
    Act Density 0.002%

    No Known Activations