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

    Neuronpedia

    INDEX
    Explanations

    state or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंजक
    0.41
    ूले
    0.36
    ስት
    0.35
     argumentos
    0.35
     dlou
    0.35
     testAvg
    0.34
    পিত
    0.34
     दिलच
    0.34
    ⊠
    0.34
    俸
    0.33
    POSITIVE LOGITS
     состояние
    3.30
     condition
    3.16
     상태
    3.02
     состояния
    3.00
    状態
    2.88
    状态
    2.83
     состоянии
    2.83
    condition
    2.80
    狀態
    2.77
     Condition
    2.67
    Act Density 0.084%

    No Known Activations