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

    Neuronpedia

    INDEX
    Explanations

    무엇을 도와드릴까요?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     h
    1.09
     ▶
    0.99
     !!
    0.94
     fared
    0.93
     ✅
    0.92
     ✔
    0.91
     is
    0.90
     achieved
    0.90
     merupakan
    0.90
     veri
    0.89
    POSITIVE LOGITS
    Convers
    0.99
    Healing
    0.98
    Philos
    0.95
    Useful
    0.95
    Collectible
    0.94
    Logging
    0.94
    Elemental
    0.94
    Ethnic
    0.94
    Collecting
    0.93
    Orden
    0.93
    Act Density 0.006%

    No Known Activations