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

    Neuronpedia

    INDEX
    Explanations

    before making or starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     전기
    0.95
     மாதிரி
    0.88
     方向
    0.87
     Governance
    0.87
    तरीय
    0.87
    amodel
    0.86
    acky
    0.86
    лук
    0.86
     pendiente
    0.85
     السي
    0.84
    POSITIVE LOGITS
     Rocco
    1.00
    pepper
    1.00
     Pepper
    1.00
     Kerry
    0.98
    クリ
    0.98
     pequena
    0.97
     Neb
    0.96
    Kelly
    0.96
    Pepper
    0.94
     pepper
    0.93
    Act Density 0.221%

    No Known Activations