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

    Neuronpedia

    INDEX
    Explanations

    recommendations and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ヘル
    0.50
    赫
    0.43
    obi
    0.42
    ail
    0.39
    ビット
    0.39
     adatt
    0.38
    🦖
    0.38
    execution
    0.38
     afflicted
    0.38
    OBI
    0.37
    POSITIVE LOGITS
     Regime
    0.47
     Watering
    0.40
     blom
    0.39
     eBooks
    0.39
     Premier
    0.36
     नज़र
    0.35
    ังสือ
    0.35
     plums
    0.35
     plung
    0.35
    бет
    0.35
    Act Density 0.006%

    No Known Activations