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

    Neuronpedia

    INDEX
    Explanations

    detailed explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    遗传
    0.43
     Catholics
    0.41
     theologian
    0.41
    腓
    0.41
    fiction
    0.39
    thememanager
    0.39
    ὖ
    0.38
    opolitical
    0.38
    ้าย
    0.38
    Seasonal
    0.38
    POSITIVE LOGITS
     Depth
    0.43
     line
    0.42
     detail
    0.42
     incluyen
    0.41
     Flags
    0.40
     detal
    0.40
     were
    0.39
     include
    0.39
     depth
    0.39
     dari
    0.38
    Act Density 0.010%

    No Known Activations